© 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. 35-TRANSCODER-HP
    7. 40210
    Prev
    Next
    INDEX
    Explanations

    mixed languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reeze
    -0.32
    oke
    -0.29
    oice
    -0.28
     spokeswoman
    -0.28
    uncture
    -0.28
    ifestyle
    -0.27
    wiki
    -0.27
    leftrightarrow
    -0.27
    outines
    -0.26
    ichever
    -0.26
    POSITIVE LOGITS
    æĦŁåĬ¨
    0.31
    dÃŃ
    0.30
    dì
    0.30
    inis
    0.29
     dap
    0.28
    tell
    0.28
     té
    0.28
    alla
    0.27
    ass
    0.27
     tell
    0.27
    Activations Density 27.130%

    No Known Activations