© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12008
    Prev
    Next
    INDEX
    Explanations

    in for loops

    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
    èĢ½
    -0.07
    squ
    -0.06
     lacking
    -0.06
    åĨł
    -0.06
    åģ¥
    -0.06
    éģ®
    -0.06
    2
    -0.06
    IP
    -0.06
    èģļåĬĽ
    -0.06
    aine
    -0.06
    POSITIVE LOGITS
    æĽ´æĸ°çļĦ
    0.10
    ToUpdate
    0.09
    æĽ´æĸ°èĩ³
    0.09
    ä¸ĢæĿ¡æĿ¡
    0.09
    ãĤĴæĽ´æĸ°
    0.08
    updates
    0.08
    Reuse
    0.08
     обнов
    0.08
    oldown
    0.08
    hammer
    0.08
    Activations Density 0.001%

    No Known Activations