© 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. 30-TRANSCODER-HP
    7. 95059
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     sucker
    -0.27
    ç»ĵæĻ¶
    -0.27
    å°¼äºļ
    -0.27
    ến
    -0.26
    uya
    -0.26
    cene
    -0.25
    å¨ĥ
    -0.24
    subs
    -0.24
    ẻ
    -0.24
    <![
    -0.23
    POSITIVE LOGITS
    isman
    0.29
    -tracking
    0.25
     mind
    0.25
    akens
    0.24
    “They
    0.24
    å¹¢
    0.24
    è§Ħ
    0.24
    æľ¬ç§ijçĶŁ
    0.23
    çľĭå¾Ĺ
    0.23
     Turner
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.