© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 126947
    Prev
    Next
    INDEX
    Explanations

    Geometry and math

    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
    Negative Logits
     complains
    -0.07
    与发展
    -0.07
     לחוק
    -0.07
     şimdi
    -0.07
    🌺
    -0.07
     cheerful
    -0.07
     rivals
    -0.07
     tackles
    -0.07
     preserves
    -0.07
     prospects
    -0.07
    POSITIVE LOGITS
    .sd
    0.07
    .b
    0.07
    adr
    0.07
    .sorted
    0.07
    ↵        
↵
    0.07
    ほと
    0.07
    _g
    0.07
     boards
    0.07
    גד
    0.06
    ughters
    0.06
    Activations Density 0.089%

    No Known Activations