© 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. 41293
    Prev
    Next
    INDEX
    Explanations

    mathematical equations with variables

    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
    æķ¢
    -0.07
    Ú©ÙĪ
    -0.07
    ä¹łä½ľ
    -0.06
    urio
    -0.06
    สู
    -0.06
    &
    -0.06
    koch
    -0.06
    é¦ĸåºľ
    -0.06
    æķ¢è¯´
    -0.06
    nbsp
    -0.06
    POSITIVE LOGITS
    ahan
    0.09
    ourke
    0.08
    ä»İä½ķ
    0.07
    धान
    0.07
    åĩºæīĭ
    0.07
    æīĭä¸ĭ
    0.07
    onte
    0.07
    inox
    0.07
    idon
    0.07
    ownik
    0.07
    Activations Density 0.018%

    No Known Activations