© 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. 16615
    Prev
    Next
    INDEX
    Explanations

    if you

    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
    benh
    -0.08
    ãģķãĤĬ
    -0.07
    çļĦæľīåĬĽ
    -0.07
    afir
    -0.07
     Ñħода
    -0.07
    áĢĺ
    -0.07
    ostream
    -0.07
    akor
    -0.07
    åħľ
    -0.07
    EXTERN
    -0.07
    POSITIVE LOGITS
    æİ¥ä¸ĭæĿ¥
    0.07
    hea
    0.07
    nore
    0.06
    é¦ĸåħĪéľĢè¦ģ
    0.06
    yo
    0.06
    ies
    0.06
    æĪij们åħĪ
    0.06
    åľ¨æİ¥ä¸ĭæĿ¥çļĦ
    0.06
    cies
    0.06
    åħ³éĶ®çļĦ
    0.06
    Activations Density 0.001%

    No Known Activations