© 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. 15-RESID-POST-AA
    11. 114969
    Prev
    Next
    INDEX
    Explanations

    G

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    หวย
    -0.08
    ✐
    -0.08
     trader
    -0.07
    首相
    -0.07
    秋季
    -0.07
    uku
    -0.07
    וצאות
    -0.07
     marché
    -0.07
    vn
    -0.07
    ⋈
    -0.07
    POSITIVE LOGITS
    totals
    0.07
     Humanities
    0.07
     Valk
    0.07
     STANDARD
    0.07
    	SP
    0.07
    利润
    0.06
    홰
    0.06
     Özellik
    0.06
     responseData
    0.06
    𬶠
    0.06
    Activations Density 0.038%

    No Known Activations