© 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. 22099
    Prev
    Next
    INDEX
    Explanations

    infrared

    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
    ä¸Ģ大æī¹
    -0.30
    /stream
    -0.29
     grate
    -0.27
    该æ¡Ī
    -0.26
    ç¢Į
    -0.26
    åĨ·åĨ·
    -0.25
    åIJĦéĥ¨éŨ
    -0.25
    icol
    -0.25
    BeginInit
    -0.25
    STREAM
    -0.25
    POSITIVE LOGITS
    hest
    0.28
    è¿
    0.28
    ellar
    0.26
     Distributed
    0.25
    ations
    0.25
    eda
    0.24
    UNT
    0.24
    æ¤Ń
    0.24
     Simulation
    0.24
    otas
    0.24
    Activations Density 0.002%

    No Known Activations