© 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. 10978
    Prev
    Next
    INDEX
    Explanations

    repeat or do anew

    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
    odel
    -0.08
    ản
    -0.07
    è¿Ľä¸ĢæŃ¥æıIJé«ĺ
    -0.07
    cius
    -0.07
    ggi
    -0.07
    BOX
    -0.07
    velt
    -0.07
     operated
    -0.07
    YPE
    -0.07
    Tool
    -0.07
    POSITIVE LOGITS
     anew
    0.14
    éĩįæĸ°
    0.12
     fresh
    0.10
    fresh
    0.10
    ä»İ头
    0.09
    ä¸Ģéģį
    0.09
    éĩįæĸ°å¼Ģå§ĭ
    0.09
    æĸ°çļĦ
    0.08
    æĸ°ä¸Ģè½®
    0.08
    åħ¨å¥Ĺ
    0.08
    Activations Density 0.085%

    No Known Activations