© 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. 60457
    Prev
    Next
    INDEX
    Explanations

    code tags and punctuation

    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
    -X
    -0.08
    æľ¬åĬŀæ³ķ
    -0.07
     ÐĹаÑĤо
    -0.07
    اÙĨÙĪÙĨ
    -0.07
    ?,
    -0.07
    ìŀ¡
    -0.07
    ?):
    -0.07
    æ½¼
    -0.07
    erber
    -0.07
     Kramer
    -0.07
    POSITIVE LOGITS
    æĪĸèĢħ
    0.09
    æĪĸåħ¶
    0.08
     or
    0.08
    æĪĸ
    0.08
    à¹Į
    0.07
     ëĺIJëĬĶ
    0.07
    æĪĸèĢħæĺ¯
    0.07
    æĪĸåľ¨
    0.07
     Hoặc
    0.07
    æĪĸ对
    0.07
    Activations Density 0.022%

    No Known Activations