© 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. 108581
    Prev
    Next
    INDEX
    Explanations

    colon and quotation mark

    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
    惕
    -0.06
    robe
    -0.06
     Acrobat
    -0.06
     Rat
    -0.06
     prone
    -0.06
    大庆
    -0.06
     fate
    -0.06
    up
    -0.06
    come
    -0.06
    igh
    -0.06
    POSITIVE LOGITS
    สถ
    0.08
    -coded
    0.07
     شخص
    0.07
    𐱅
    0.07
    imensional
    0.07
     communal
    0.07
    .FieldName
    0.07
    opacity
    0.07
    阱
    0.07
    ומות
    0.07
    Activations Density 0.080%

    No Known Activations