© 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 EvalsExportsAPI 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. 77459
    Prev
    Next
    INDEX
    Explanations

    drug names

    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
     Bau
    -0.06
    采
    -0.06
    Ans
    -0.06
    Tra
    -0.06
     fuer
    -0.06
    ش
    -0.06
    共同体
    -0.06
    千方百
    -0.06
    Kin
    -0.06
    封面
    -0.06
    POSITIVE LOGITS
    洫
    0.07
     Predicate
    0.07
    .Decimal
    0.07
     Fiscal
    0.07
    (boolean
    0.07
     exemple
    0.07
    購物
    0.07
     Instead
    0.06
    (ap
    0.06
    십시오
    0.06
    Activations Density 0.003%

    No Known Activations