© 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. 35-TRANSCODER-HP
    7. 40549
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     crow
    -0.29
    æŶè£ħ
    -0.28
    æĬ½å¥ĸ
    -0.28
    icious
    -0.26
    ç´ł
    -0.25
    Sortable
    -0.25
    _handlers
    -0.25
    еÑģп
    -0.24
     Crow
    -0.24
    ety
    -0.24
    POSITIVE LOGITS
    åħŃåIJĪ
    0.28
    poke
    0.27
    bec
    0.27
     computed
    0.26
    çļĦæŃ¥ä¼IJ
    0.26
    ç®Ķ
    0.25
    abelle
    0.25
    ä¹Łä¸į
    0.25
    çıĢ
    0.25
     agree
    0.24
    Activations Density 12.716%

    No Known Activations

    This feature has no known activations.