© 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. 22484
    Prev
    Next
    INDEX
    Explanations

    spike wave

    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
    è°¦
    -0.07
    iknya
    -0.07
    è¬Ļ
    -0.07
    sko
    -0.07
    lessly
    -0.07
    åĪ°çļĦ
    -0.06
    è¿Ľåħ¥åĪ°
    -0.06
    illage
    -0.06
    åıªæĺ¯ä¸Ģ
    -0.06
    andar
    -0.06
    POSITIVE LOGITS
     Hatta
    0.08
    æľīåĬĽ
    0.08
    empre
    0.07
    æľīéĴĪ对æĢ§
    0.07
    .RunWith
    0.07
    azzi
    0.07
    æľīåĬĽçļĦ
    0.07
    iel
    0.07
    æĢ§æĪĸ
    0.07
    orrent
    0.06
    Activations Density 0.002%

    No Known Activations