© 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. 21342
    Prev
    Next
    INDEX
    Explanations

    not an issue, no thing, not know much

    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
    ä¸½å¨ľ
    -0.07
    NonNull
    -0.07
    é¼ĵ
    -0.07
    æĪijçıŃ
    -0.07
    è¹ĭ
    -0.06
    æ³Į
    -0.06
    ëĭ¥
    -0.06
    idon
    -0.06
    زÙĬد
    -0.06
    æĸĻæľº
    -0.06
    POSITIVE LOGITS
     anymore
    0.10
    æľīä»»ä½ķ
    0.10
    ä»»ä½ķéĹ®é¢ĺ
    0.10
     whatsoever
    0.09
    ä»»ä½ķ责任
    0.08
     أبد
    0.08
    æIJŃçIJĨ
    0.08
    ä½Ĩåı¯ä»¥
    0.08
     altogether
    0.08
    好æŃ¹
    0.08
    Activations Density 0.071%

    No Known Activations