© 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. 32-TRANSCODER-HP
    7. 40986
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     refere
    -0.28
    /ubuntu
    -0.27
    æĪIJ份
    -0.27
    纪å½ķ
    -0.26
    mojom
    -0.26
    ä¸Ģèĩ´æĢ§
    -0.26
     specialization
    -0.25
    uble
    -0.25
    æĸ¹ä½į
    -0.25
     polarization
    -0.24
    POSITIVE LOGITS
     {...
    0.26
    æĪªæŃ¢
    0.26
    ling
    0.24
     forts
    0.24
    ovan
    0.24
    _timeout
    0.23
    .timedelta
    0.23
    寻
    0.23
    çĶŁçī©åѦ
    0.23
    xic
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.