© 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. 22-TRANSCODER-HP
    7. 112916
    Prev
    Next
    INDEX
    Explanations

    Stones and calculus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -original
    -0.28
    ichi
    -0.27
    ä¼ijæģ¯
    -0.25
    ä½¥
    -0.25
     Outlet
    -0.25
    acha
    -0.25
    缸éĢļ
    -0.25
    éĩįåIJ¯
    -0.25
    uo
    -0.24
    人æĸĩ
    -0.24
    POSITIVE LOGITS
    åĽ¾çīĩæĿ¥æºIJ
    0.29
     Favorites
    0.28
    fusion
    0.26
    çĮ·
    0.25
     dreaded
    0.25
    ï¼Ħ
    0.24
     Cascade
    0.24
    TypeDef
    0.24
    æĤ£èĢħçļĦ
    0.24
     VIDEO
    0.23
    Activations Density 0.011%

    No Known Activations