© 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. 12-TRANSCODER-HP
    7. 24121
    Prev
    Next
    INDEX
    Explanations

    satellite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĬĪ
    -0.28
    inality
    -0.28
    è¿ĻæĿ¡
    -0.27
    åĽ½æĹĹ
    -0.25
     Mandal
    -0.25
    inary
    -0.24
    hton
    -0.24
    bilt
    -0.23
     tearing
    -0.23
    icip
    -0.23
    POSITIVE LOGITS
    kj
    0.29
    REM
    0.29
     rem
    0.27
    课å¤ĸ
    0.26
     survey
    0.25
     Rem
    0.24
    nj
    0.24
     Há
    0.24
    rem
    0.24
     jam
    0.24
    Activations Density 0.001%

    No Known Activations