© 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. 27-TRANSCODER-HP
    7. 8111
    Prev
    Next
    INDEX
    Explanations

    fields of study

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĿŀ常åĸľæ¬¢
    -0.25
    éĨħ
    -0.24
    æĬ¥ä»·
    -0.24
    sa
    -0.24
    acen
    -0.24
    sed
    -0.23
    请åģĩ
    -0.23
    band
    -0.23
    ÑĢон
    -0.23
     manoe
    -0.23
    POSITIVE LOGITS
     biology
    0.28
     psychology
    0.26
    uchen
    0.26
     anthropology
    0.26
     Bridges
    0.26
     emerged
    0.26
    à°¬
    0.26
     science
    0.26
    ä¸ºçĽ®æłĩ
    0.26
     researchers
    0.25
    Activations Density 0.003%

    No Known Activations