© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 18924
    Prev
    Next
    INDEX
    Explanations

    Code and Non-English words

    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
    ç±³ç²ī
    -0.27
    алÑĮн
    -0.26
    .construct
    -0.26
    æ¹ĸåĮº
    -0.26
    æ¹ĸ
    -0.25
    ç³Ļ
    -0.24
     collective
    -0.24
    actal
    -0.24
    \b
    -0.23
    ASY
    -0.23
    POSITIVE LOGITS
    dı
    0.30
    ä¸ĭ乡
    0.26
    ipt
    0.26
    _story
    0.25
    æľĢ强
    0.25
    Dic
    0.25
    ä¸ĢæĹ¥
    0.25
    EA
    0.25
    -day
    0.24
    weed
    0.24
    Activations Density 0.791%

    No Known Activations