© 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. 32-TRANSCODER-HP
    7. 41596
    Prev
    Next
    INDEX
    Explanations

    food science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bez
    -0.28
     fictional
    -0.28
    zilla
    -0.27
     crowned
    -0.26
    ÅĦst
    -0.26
    izzer
    -0.26
    éĢ£çµIJ
    -0.25
    åĩºè·¯
    -0.25
     dwell
    -0.25
    éģĵ
    -0.25
    POSITIVE LOGITS
    gal
    0.32
     gal
    0.32
    posição
    0.31
     lac
    0.30
     Gal
    0.30
    Gal
    0.29
     latch
    0.29
    æ£ķ
    0.27
    glob
    0.27
     lact
    0.26
    Activations Density 0.003%

    No Known Activations