© 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. 19877
    Prev
    Next
    INDEX
    Explanations

    Ver

    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
    Negative Logits
    ori
    -0.32
    à¸İ
    -0.28
    .sav
    -0.26
    梦
    -0.25
     ideal
    -0.24
    /rc
    -0.23
     downloads
    -0.23
    oric
    -0.23
    affle
    -0.23
     [][]
    -0.23
    POSITIVE LOGITS
    å±Ģ
    0.30
    orno
    0.29
    çģµæ´»
    0.26
     Wolff
    0.25
    etail
    0.25
    å±Ģéķ¿
    0.25
    _window
    0.25
    æĹłä¸į
    0.24
    .flex
    0.24
     flexible
    0.24
    Activations Density 0.006%

    No Known Activations