© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 111411
    Prev
    Next
    INDEX
    Explanations

    suggestions or instructions

    np_max-act · gemini-2.0-flash

    sentences or clauses that introduce multiple options or steps (e.g., openings that say "There are several/ many ways" or otherwise present a list of methods).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      ↵  ↵
    -0.07
     nuisance
    -0.07
     Lands
    -0.07
    .Drawable
    -0.06
    مادة
    -0.06
    켜
    -0.06
     cantidad
    -0.06
     consumes
    -0.06
     dataTable
    -0.06
     outra
    -0.06
    POSITIVE LOGITS
     Be
    0.07
    ⚛
    0.07
    怎么办
    0.06
     Bre
    0.06
     Too
    0.06
    .POST
    0.06
     propagation
    0.06
    ኍ
    0.06
    ┻
    0.06
     wheel
    0.06
    Activations Density 0.152%

    No Known Activations