© 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. 142594
    Prev
    Next
    INDEX
    Explanations

    problems or limitations

    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
    ä¸Ģ个人
    -0.29
    éĢļçŁ¥
    -0.26
    /he
    -0.26
    ptr
    -0.25
    æ¯Ķå¦Ĥ说
    -0.25
    _PTR
    -0.25
    ÑĤи
    -0.24
    ä¼ļè§īå¾Ĺ
    -0.24
    ording
    -0.24
    åŀ®
    -0.24
    POSITIVE LOGITS
    omens
    0.34
     <!--[
    0.26
    omen
    0.25
    ‘
    0.25
     given
    0.24
    æĢĽ
    0.24
    ä¸ĩ个
    0.24
     writeTo
    0.24
    ä¸ĩåIJį
    0.24
    æѦ
    0.23
    Activations Density 13.910%

    No Known Activations