© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29446
    Prev
    Next
    INDEX
    Explanations

    указ

    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
    玩游戏
    -0.08
    奶奶
    -0.08
    送货
    -0.07
    接送
    -0.07
    דרך
    -0.07
     reasoning
    -0.07
    踣
    -0.07
    -cmpr
    -0.07
    ncia
    -0.07
    .Java
    -0.07
    POSITIVE LOGITS
     alteration
    0.08
    债务
    0.07
     resort
    0.07
    _ab
    0.07
    fit
    0.06
     hal
    0.06
    [channel
    0.06
     chú
    0.06
    associated
    0.06
    这一切
    0.06
    Activations Density 0.017%

    No Known Activations