© 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. 77928
    Prev
    Next
    INDEX
    Explanations

    chemical

    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
     irresistible
    -0.09
    ermalink
    -0.08
    .Buffered
    -0.07
    ERGY
    -0.07
     Phar
    -0.07
     discourage
    -0.07
     ^=
    -0.07
    [parent
    -0.07
    折磨
    -0.07
     spécialisé
    -0.07
    POSITIVE LOGITS
    ۅ
    0.07
    ole
    0.07
    -$
    0.07
     spl
    0.07
     |↵
    0.07
    `↵↵
    0.06
    '];
↵
    0.06
    Comment
    0.06
     transaction
    0.06
     Municipal
    0.06
    Activations Density 0.001%

    No Known Activations