© 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. 56693
    Prev
    Next
    INDEX
    Explanations

    sequences of digits

    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¸ĭåIJĮ
    -0.07
    ...
    -0.06
    ä¾Ŀæ³ķ追究责任
    -0.06
    		  ↵
    -0.06
    LP
    -0.06
     Branco
    -0.05
    &
    -0.05
    /utility
    -0.05
    å¾Ĺä¸į
    -0.05
    XXX
    -0.05
    POSITIVE LOGITS
    osat
    0.08
    hiba
    0.08
    örde
    0.08
     Sinon
    0.08
    omÄĽ
    0.08
    æľ¬æ¥¼
    0.08
    ?,?,?,?,
    0.08
    æľ¬åľºæ¯ĶèµĽ
    0.08
    ÏĦÎŃÏģ
    0.08
    Tester
    0.08
    Activations Density 0.056%

    No Known Activations