© 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. 20-TRANSCODER-HP
    7. 140754
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     mat
    -0.30
    å®ĮæĪIJåIJİ
    -0.27
    åı³
    -0.25
    .mat
    -0.25
    born
    -0.25
    sock
    -0.25
    çĹħæ¯ĴæĦŁæŁĵ
    -0.25
    .ot
    -0.24
     маÑĤ
    -0.24
    ddie
    -0.24
    POSITIVE LOGITS
    eur
    0.25
    éĬ·
    0.25
    æĭĸ
    0.24
    ä»·
    0.24
    uai
    0.23
    (price
    0.23
    isol
    0.23
    urai
    0.23
     oral
    0.23
     Ass
    0.23
    Activations Density 6.645%

    No Known Activations