© 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. 24-TRANSCODER-HP
    7. 149478
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OfDay
    -0.30
     cú
    -0.28
    KeyPressed
    -0.27
    em
    -0.26
     appearing
    -0.26
    åħ¥æĪ·
    -0.26
     cán
    -0.26
    .choice
    -0.25
     parade
    -0.25
    InputChange
    -0.25
    POSITIVE LOGITS
    ç®Ģ
    0.33
    zion
    0.31
    çĽ²
    0.30
    æľºåľº
    0.27
    彩
    0.27
    öl
    0.27
    ulous
    0.26
     tá»ĭch
    0.26
    >>↵↵
    0.26
    &type
    0.26
    Activations Density 0.684%

    No Known Activations

    This feature has no known activations.