© 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. 62951
    Prev
    Next
    INDEX
    Explanations

    Myths, legends, and stories

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĦıä¹ī
    -0.27
    ä¹ī
    -0.26
    åĿIJä¸ĭ
    -0.26
    Ahead
    -0.25
    .angular
    -0.25
    orio
    -0.24
    çĵĴ
    -0.24
    fram
    -0.24
    tein
    -0.24
    ellaneous
    -0.24
    POSITIVE LOGITS
    åĴĮ个人
    0.29
    ä¼łéĹ»
    0.26
     onPostExecute
    0.25
    nas
    0.24
    Assert
    0.24
    üst
    0.23
    GBT
    0.23
    æĬ¥éģĵ
    0.23
    ombo
    0.23
    åijĬè¯ī她
    0.23
    Activations Density 9.348%

    No Known Activations