© 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. 15-RESID-POST-AA
    11. 17034
    Prev
    Next
    INDEX
    Explanations

    maid

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chooses
    -0.07
     Soil
    -0.07
    	document
    -0.07
    /player
    -0.07
    .char
    -0.07
    _ADV
    -0.07
    夢
    -0.07
    ?"
    -0.07
     Destructor
    -0.06
     spiritually
    -0.06
    POSITIVE LOGITS
    ῐ
    0.07
    omencl
    0.07
     KW
    0.07
    cılı
    0.06
     بسبب
    0.06
    DAL
    0.06
     replaced
    0.06
    也能
    0.06
    مواقف
    0.06
     squ
    0.06
    Activations Density 0.001%

    No Known Activations