© 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. 14582
    Prev
    Next
    INDEX
    Explanations

    ways, types, categories, methods

    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
    sic
    -0.08
    äºļ
    -0.07
    第ä¸īä½į
    -0.07
     etc
    -0.07
    åİĭæł¹
    -0.06
     ÙħÙĨÙĩ
    -0.06
    çİĭèĢħ
    -0.06
    第äºĮä½į
    -0.06
    rij
    -0.06
     e
    -0.06
    POSITIVE LOGITS
    æľī以ä¸ĭ
    0.16
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.13
    主è¦ģåĪĨ为
    0.13
    æľīä¸ĭåĪĹ
    0.13
    以ä¸ĭåĩłç§į
    0.12
    以ä¸ĭåĩłä¸ª
    0.12
    以ä¸ĭçļĦ
    0.12
    以ä¸ĭåĩłçĤ¹
    0.12
    以ä¸ĭåĩł
    0.11
    主è¦ģæľī
    0.11
    Activations Density 0.756%

    No Known Activations