Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30009
    Prev
    Next
    INDEX
    Explanations

    beat

    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
    有很大的
    -0.07
    Navigator
    -0.07
     OUTER
    -0.07
    很
    -0.07
    Launch
    -0.07
     вс
    -0.07
     Towers
    -0.07
    כות
    -0.07
     ViewState
    -0.06
    viewController
    -0.06
    POSITIVE LOGITS
    昄
    0.07
     prostituer
    0.07
    햊
    0.07
    Specifications
    0.07
    责编
    0.07
    習慣
    0.06
     lcd
    0.06
    城市建设
    0.06
    唱
    0.06
    𝙯
    0.06
    Activations Density 0.007%

    No Known Activations