© 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. 29044
    Prev
    Next
    INDEX
    Explanations

    doesn

    np_max-act · gemini-2.0-flash

    stems of n’t-style negative contractions (the verb fragment immediately before the apostrophe-t).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ôi
    -0.07
    getMockBuilder
    -0.07
    ⇧
    -0.07
    ﾖ
    -0.07
    璒
    -0.07
     حين
    -0.07
    ㎖
    -0.07
    EQUAL
    -0.07
    씐
    -0.07
    geometry
    -0.06
    POSITIVE LOGITS
    uid
    0.07
    _frag
    0.07
    🎙
    0.06
    _patches
    0.06
     titre
    0.06
     месяц
    0.06
     lex
    0.06
    .providers
    0.06
    }`)↵
    0.06
     textbox
    0.06
    Activations Density 0.022%

    No Known Activations