© 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. 29060
    Prev
    Next
    INDEX
    Explanations

    CBC

    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
    تأكد
    -0.08
    _abs
    -0.07
    onda
    -0.07
     diagnosis
    -0.07
    ço
    -0.07
    ito
    -0.07
    核实
    -0.07
    -this
    -0.07
    now
    -0.07
    Processed
    -0.07
    POSITIVE LOGITS
    キャンペ
    0.08
    翎
    0.07
    のご
    0.07
    __":↵
    0.07
    のように
    0.07
    👋
    0.07
    玩家朋友
    0.07
    水
    0.07
     zusammen
    0.07
    の中で
    0.07
    Activations Density 0.002%

    No Known Activations