© 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. 11-RESID-POST-AA
    11. 70614
    Prev
    Next
    INDEX
    Explanations

    reciprocating pumps/machines

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     construed
    -0.07
    在我看来
    -0.07
    .Draw
    -0.07
     שבה
    -0.07
    不懂
    -0.07
    눉
    -0.07
    思考
    -0.07
    岔
    -0.07
     Unblock
    -0.07
     amnesty
    -0.07
    POSITIVE LOGITS
    Phi
    0.08
    ได
    0.07
     Multi
    0.07
    utom
    0.07
    utos
    0.07
     usable
    0.07
    vider
    0.06
     entra
    0.06
    iloc
    0.06
    icios
    0.06
    Activations Density 0.001%

    No Known Activations