© 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. 18-TRANSCODER-HP
    7. 90152
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĢ»éĿ¢ç§¯
    -0.30
    edBy
    -0.29
    wand
    -0.28
    é«ĺæĸ°
    -0.26
    iale
    -0.26
     Areas
    -0.25
    Areas
    -0.25
    个æľĪåĨħ
    -0.24
    elage
    -0.24
    ä¸įä¿¡
    -0.24
    POSITIVE LOGITS
    èijļ
    0.28
    ç®Ģ
    0.26
    袱
    0.26
     Premiership
    0.26
     ngh
    0.25
     proxies
    0.25
    MER
    0.25
    æ´»ä¸ĭåİ»
    0.24
    amarin
    0.24
    ÄŃ
    0.23
    Activations Density 61.286%

    No Known Activations

    This feature has no known activations.