© 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. 19985
    Prev
    Next
    INDEX
    Explanations

    Computer code and Earth observations

    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
    è¡Įä¸ļä¸Ń
    -0.27
    -eslint
    -0.25
    bew
    -0.25
    游æĪıä¸Ń
    -0.25
    ÃŃd
    -0.25
    åģĥ
    -0.25
    æİĴ
    -0.25
     taste
    -0.25
    åŁĭ
    -0.24
    康
    -0.24
    POSITIVE LOGITS
    ignKey
    0.28
     attractiveness
    0.26
    SPACE
    0.26
    asures
    0.24
    space
    0.24
    TES
    0.24
    atts
    0.24
     Stake
    0.24
    ATIC
    0.24
    ammer
    0.23
    Activations Density 0.948%

    No Known Activations