© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108684
    Prev
    Next
    INDEX
    Explanations

    Research reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    HttpException
    -0.27
     adjud
    -0.25
    gz
    -0.25
    oreal
    -0.25
    apos
    -0.24
     Worcester
    -0.24
    gregate
    -0.24
    æŀĭ
    -0.24
    aston
    -0.24
    ergic
    -0.23
    POSITIVE LOGITS
    LIB
    0.30
     visibility
    0.27
    -element
    0.26
     Ent
    0.26
    踪
    0.25
     Elem
    0.25
    æģIJ
    0.25
    æĢ¨
    0.25
    -proxy
    0.25
    ä¸ī天
    0.24
    Activations Density 60.320%

    No Known Activations