Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 71509
    Prev
    Next
    INDEX
    Explanations

    Code/math context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    钓
    -0.07
    .docs
    -0.07
     الدولي
    -0.07
    цеп
    -0.07
     ersten
    -0.07
    _cli
    -0.07
    打招呼
    -0.07
    聒
    -0.07
    Js
    -0.06
    寥
    -0.06
    POSITIVE LOGITS
     Susan
    0.07
    默
    0.06
    Bas
    0.06
     STA
    0.06
    quire
    0.06
    售后
    0.06
     S
    0.06
     Mur
    0.06
    身材
    0.06
     onwards
    0.06
    Activations Density 0.003%

    No Known Activations