© 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. 64573
    Prev
    Next
    INDEX
    Explanations

    Organizations

    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
    iliated
    -0.29
    -fit
    -0.27
    ĤŃ
    -0.26
    /body
    -0.26
    ä¸Ĭè°ĥ
    -0.25
    ä¸ĢæĿ¡é¾Ļ
    -0.25
    ç¬ijèĦ¸
    -0.25
    hoot
    -0.25
     vess
    -0.25
    anged
    -0.25
    POSITIVE LOGITS
    åĺİ
    0.30
    é¦
    0.26
     Irving
    0.25
     others
    0.24
    赤
    0.24
    æ¯Ķäºļ
    0.23
    .isSelected
    0.23
    atum
    0.23
    _REFER
    0.23
     reign
    0.23
    Activations Density 2.227%

    No Known Activations