© 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. 58240
    Prev
    Next
    INDEX
    Explanations

    of

    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
    звон
    -0.07
     дог
    -0.07
    clipse
    -0.07
    Thinking
    -0.07
    otions
    -0.07
    qrt
    -0.07
     assertFalse
    -0.06
     abroad
    -0.06
    crire
    -0.06
    انتخاب
    -0.06
    POSITIVE LOGITS
    ítica
    0.07
    izzas
    0.07
     NIL
    0.07
     fists
    0.07
    ddit
    0.07
     berk
    0.07
    נק
    0.07
     mg
    0.07
    Fake
    0.06
    淳
    0.06
    Activations Density 0.013%

    No Known Activations