© 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. 7-RESID-POST-AA
    11. 8089
    Prev
    Next
    INDEX
    Explanations

    Science

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    مراك
    -0.07
    inputEmail
    -0.07
     unbearable
    -0.07
    התפתחות
    -0.07
     unforgettable
    -0.07
    瘋
    -0.07
    @foreach
    -0.07
    مقار
    -0.07
    上百
    -0.06
     ParameterDirection
    -0.06
    POSITIVE LOGITS
     Science
    0.07
    =G
    0.07
    тир
    0.07
    チャー
    0.07
    ункци
    0.07
    late
    0.07
     Chan
    0.07
    Asked
    0.06
     Singer
    0.06
    zen
    0.06
    Activations Density 0.014%

    No Known Activations