© 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. 19459
    Prev
    Next
    INDEX
    Explanations

    technical subjects

    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
     converters
    -0.28
     unite
    -0.27
     pay
    -0.26
    æĶ»åĬ¿
    -0.25
    ĥģ
    -0.25
    并ä¸įå¤ļ
    -0.25
    verter
    -0.24
     Converter
    -0.24
    temporary
    -0.24
    à´§
    -0.24
    POSITIVE LOGITS
    她说
    0.29
    liche
    0.27
    akan
    0.27
    ik
    0.27
    rolling
    0.26
     Karl
    0.25
    icação
    0.25
     rolls
    0.25
    oral
    0.25
     rolled
    0.24
    Activations Density 0.819%

    No Known Activations