© 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. 20-TRANSCODER-HP
    7. 141669
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľĪ以æĿ¥
    -0.30
    aid
    -0.25
    çļĦåĬĽéĩı
    -0.24
    mund
    -0.24
    åĨįæĿ¥
    -0.24
    커
    -0.24
    éĴĴ
    -0.24
    terminated
    -0.24
    åģļå®Į
    -0.23
    太ä¹ħ
    -0.23
    POSITIVE LOGITS
    browse
    0.29
    çī¹åĪ«æĺ¯åľ¨
    0.26
     lac
    0.26
    /browser
    0.25
     labeled
    0.25
    ogr
    0.23
    och
    0.23
    Gtk
    0.23
     closest
    0.23
    xEE
    0.23
    Activations Density 60.417%

    No Known Activations