© 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. 15-RESID-POST-AA
    11. 121504
    Prev
    Next
    INDEX
    Explanations

    derivatives and math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acess
    -0.07
     coordinating
    -0.07
    🎌
    -0.07
    .syntax
    -0.06
     jsx
    -0.06
    xt
    -0.06
    ue
    -0.06
    ⵍ
    -0.06
     whoever
    -0.06
    疹
    -0.06
    POSITIVE LOGITS
     lamb
    0.07
     URL
    0.07
    نشأ
    0.07
    ;"↵
    0.07
     glyphs
    0.07
    朳
    0.06
    Neo
    0.06
    (pe
    0.06
     העוב
    0.06
    ","",
    0.06
    Activations Density 0.004%

    No Known Activations