© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 38751
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    医用
    -0.08
     Kramer
    -0.07
     testified
    -0.07
    xCB
    -0.07
    <Audio
    -0.07
     FOLLOW
    -0.07
    婚后
    -0.07
     вой
    -0.06
    正规
    -0.06
    Stmt
    -0.06
    POSITIVE LOGITS
     fucks
    0.07
     letra
    0.07
    (ag
    0.07
    -east
    0.07
    /meta
    0.07
    .where
    0.07
    arena
    0.07
    自己的
    0.07
    се
    0.06
    -awesome
    0.06
    Activations Density 0.109%

    No Known Activations