© 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. 31-TRANSCODER-HP
    7. 19617
    Prev
    Next
    INDEX
    Explanations

    they

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enti
    -0.28
    pta
    -0.26
    ocy
    -0.24
    趣
    -0.24
    ä½łçľĭ
    -0.24
     filmy
    -0.24
    没人
    -0.24
    ÃŃc
    -0.23
    óst
    -0.23
     entra
    -0.23
    POSITIVE LOGITS
    æĺ¯
    0.59
    å°±æĺ¯
    0.47
     lÃł
    0.46
    åĪĻæĺ¯
    0.44
     adalah
    0.44
     is
    0.43
    æĺ¯åľ¨
    0.43
    å°±æĺ¯åľ¨
    0.41
     æĺ¯
    0.41
    æĺ¯ä»ĸ
    0.40
    Activations Density 0.149%

    No Known Activations