© 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. 22-TRANSCODER-HP
    7. 111041
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .XR
    -0.27
    nen
    -0.27
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.26
    è¿Ļæł·åģļ
    -0.26
    è¨ĵ
    -0.25
    izen
    -0.25
    ὶ
    -0.24
    躬
    -0.24
    .ix
    -0.24
    çĥ
    -0.24
    POSITIVE LOGITS
    anghai
    0.29
     pertinent
    0.27
    isArray
    0.26
    ç§ijåѦéĻ¢
    0.24
    ANNEL
    0.24
     verd
    0.23
     вал
    0.23
    оÑģÑĮ
    0.23
     ceiling
    0.23
    å¥Ĺ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.