© 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. 108441
    Prev
    Next
    INDEX
    Explanations

    ive

    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
    مناطق
    -0.07
    '])->
    -0.07
    .setBackground
    -0.07
    better
    -0.07
    为主题的
    -0.07
    .isTrue
    -0.07
     أنحاء
    -0.07
     Nacht
    -0.06
    scenes
    -0.06
     richer
    -0.06
    POSITIVE LOGITS
     Daniel
    0.08
    สถ
    0.08
     độ
    0.08
    taş
    0.07
    ?”
    0.07
     alloys
    0.07
    auce
    0.07
    units
    0.06
    IVEN
    0.06
     Nico
    0.06
    Activations Density 0.004%

    No Known Activations