© 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. 31-TRANSCODER-HP
    7. 17791
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     newVal
    -0.26
    inality
    -0.25
    æį¢äºĨ
    -0.25
     forfe
    -0.25
    teenth
    -0.24
    æķ²
    -0.24
    imate
    -0.24
    usher
    -0.24
    getParam
    -0.24
    èľ
    -0.23
    POSITIVE LOGITS
    ä¸ŃåĽ½åĪ¶éĢł
    0.29
    åĽĬ
    0.28
    OfYear
    0.27
    ayout
    0.27
    =@
    0.25
    vern
    0.25
    温馨
    0.25
     yn
    0.24
    æµİ
    0.24
    elles
    0.24
    Activations Density 0.279%

    No Known Activations

    This feature has no known activations.