© 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. 33251
    Prev
    Next
    INDEX
    Explanations

    technical project components

    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
    .Encoding
    -0.07
    INGK
    -0.07
    Ipv
    -0.07
    æĿIJè´¨çļĦ
    -0.07
    æĿİçİī
    -0.07
    anka
    -0.07
     manh
    -0.07
    aeda
    -0.07
    æĿ¥æĦĪ
    -0.07
    egner
    -0.07
    POSITIVE LOGITS
     Cano
    0.08
    æĪĸ缴æİ¥
    0.07
    æ¶İ
    0.06
    çļĦè¿ĺæĺ¯
    0.06
    \Container
    0.06
     Sage
    0.06
    é¦ĸ
    0.06
     Toma
    0.06
    æĹłåħ³
    0.06
    äºĨåIJĹ
    0.06
    Activations Density 0.036%

    No Known Activations