© 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. 32-TRANSCODER-HP
    7. 41024
    Prev
    Next
    INDEX
    Explanations

    calories and diet

    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
    Negative Logits
     cal
    -0.38
    ibrate
    -0.27
    åĽĽä½į
    -0.27
    æł¡
    -0.27
     Gib
    -0.26
     energy
    -0.26
    çļĦèĥ½éĩı
    -0.26
    tbl
    -0.25
    _energy
    -0.25
    æīĵæĸŃ
    -0.25
    POSITIVE LOGITS
    æ§IJ
    0.30
    éĵĥ
    0.28
    olia
    0.27
    HD
    0.26
    æŃ¢
    0.25
    é£ŁçĶ¨
    0.24
    (Input
    0.24
     Meal
    0.24
     ç»ĵ
    0.24
    ades
    0.24
    Activations Density 0.001%

    No Known Activations