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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41155
    Prev
    Next
    INDEX
    Explanations

    <

    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
    委会
    -0.09
     stylesheet
    -0.07
    我又
    -0.07
    Everything
    -0.07
    ◡
    -0.07
    很开心
    -0.07
     SB
    -0.06
    唰
    -0.06
    抖
    -0.06
    /share
    -0.06
    POSITIVE LOGITS
    _da
    0.07
    _atts
    0.07
     patent
    0.07
     ctl
    0.07
     instruct
    0.07
    称号
    0.07
    construct
    0.07
     Rockets
    0.07
    ≪
    0.07
     exemplo
    0.07
    Activations Density 0.011%

    No Known Activations