© 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. 2524
    Prev
    Next
    INDEX
    Explanations

    struct, basic, lib, `static void`, `data class`, `typename T>`

    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
     Äijá»ijc
    -0.07
    ä¸į管
    -0.07
    大åĬŁ
    -0.07
    ier
    -0.07
    ÑĺÑĥ
    -0.07
    utely
    -0.07
    ually
    -0.07
    举ä¾ĭ
    -0.07
    träg
    -0.07
    -0.06
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.09
    ĥģ
    0.08
    astiche
    0.08
    hasta
    0.08
    ekon
    0.07
    सर
    0.07
    è·ĥè·ĥ欲è¯ķ
    0.07
    !»
    0.07
    æ½¢
    0.07
    ante
    0.07
    Activations Density 0.030%

    No Known Activations