© 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. 131046
    Prev
    Next
    INDEX
    Explanations

    technical contexts

    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
    åĸľ
    -0.31
    åī
    -0.29
    éĢĹ
    -0.28
    æĻĵ
    -0.27
    è¿IJ
    -0.27
    å·±
    -0.26
    sic
    -0.26
    æ¸ħæ¥ļ
    -0.26
    ç½²
    -0.26
    ri
    -0.26
    POSITIVE LOGITS
    éĽī
    0.28
    ç®Ķ
    0.27
    IJľ
    0.26
    CEF
    0.26
    éĥ¨åĪĨåĨħ容
    0.25
    æĦı大
    0.24
    faces
    0.24
    scriptId
    0.24
    è¯Ħä»·
    0.23
    ä¸įåIJĮæĦı
    0.23
    Activations Density 1.350%

    No Known Activations