© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31413
    Prev
    Next
    INDEX
    Explanations

    function arguments and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .yahoo
    -0.07
    matches
    -0.06
    麻
    -0.06
    itier
    -0.06
     fundamental
    -0.06
    aminer
    -0.06
    æĨij
    -0.06
    ago
    -0.06
    åĩŃçĿĢ
    -0.06
     martin
    -0.06
    POSITIVE LOGITS
    åİ»æİī
    0.08
    åİ»éĻ¤
    0.08
    移éĻ¤
    0.08
    ην
    0.08
    åİŁæľ¬
    0.08
    çĭ¬åįł
    0.07
    ubr
    0.07
    æĪĸ缺
    0.07
     entfernen
    0.07
    ToRemove
    0.07
    Activations Density 0.069%

    No Known Activations