© 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. 90099
    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
    compare
    -0.30
     compare
    -0.29
    pron
    -0.29
    ç»Ļä»ĸ们
    -0.28
    »¿
    -0.27
    è´Ŀ
    -0.26
    è®°å¾Ĺ
    -0.25
    °F
    -0.25
    æħ°
    -0.25
    æľĽ
    -0.25
    POSITIVE LOGITS
    rats
    0.28
    Fabric
    0.26
    alyzed
    0.26
    /slick
    0.25
     CONTRIBUTORS
    0.25
     attractions
    0.25
    owanie
    0.24
    ¢åįķ
    0.24
    rike
    0.24
    çIJ¦
    0.24
    Activations Density 1.202%

    No Known Activations

    This feature has no known activations.