© 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. 42577
    Prev
    Next
    INDEX
    Explanations

    Genes

    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
     Ży
    -0.29
    ego
    -0.28
    ONTAL
    -0.27
    ëŀĦ
    -0.26
     createAction
    -0.26
    è¿ŁåĪ°
    -0.26
    å¼ĢåĪĽ
    -0.25
    quarters
    -0.25
    /calendar
    -0.25
    æĹłæīĢè°ĵ
    -0.24
    POSITIVE LOGITS
     gene
    0.31
     tink
    0.30
     expression
    0.30
     sp
    0.30
     genetic
    0.29
    (expr
    0.29
    æºľ
    0.29
     sn
    0.29
    /gen
    0.29
    ngen
    0.29
    Activations Density 0.002%

    No Known Activations