© 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. 25-TRANSCODER-HP
    7. 109466
    Prev
    Next
    INDEX
    Explanations

    fast and easy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸į稳å®ļ
    -0.27
     Legs
    -0.27
    marsh
    -0.26
    è¿Ļ项
    -0.26
    Paris
    -0.25
    èıľèĤ´
    -0.25
    è¿Ļ件äºĭæĥħ
    -0.25
    è«ĸ
    -0.24
    æĺĵäºİ
    -0.24
    organizations
    -0.24
    POSITIVE LOGITS
     behavior
    0.29
    иÑĢовка
    0.29
    pcf
    0.28
     performance
    0.27
     zoning
    0.27
     behavioral
    0.26
    uchos
    0.26
     execution
    0.26
    าย
    0.26
     nature
    0.25
    Activations Density 0.916%

    No Known Activations