© 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. 56314
    Prev
    Next
    INDEX
    Explanations

    periods of absence or interruption

    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¸įæĸŃå¢ŀåĬł
    -0.08
    éĢIJæ¸IJ
    -0.08
    sett
    -0.08
    ä»İä¸Ģå¼Ģå§ĭ
    -0.08
    же
    -0.08
    æĹ¥æ¸IJ
    -0.08
    uniq
    -0.08
    صب
    -0.08
    éĢIJæŃ¥å½¢æĪIJ
    -0.08
    éĢIJå¹´
    -0.07
    POSITIVE LOGITS
    éĹ´æĸŃ
    0.13
    éĹ´éļĶ
    0.12
    ä¸ŃæĸŃ
    0.12
    éĹ´éļĻ
    0.12
    ä¼ijçľł
    0.11
     hiatus
    0.11
     briefly
    0.11
     temporarily
    0.11
    åĽŀæĿ¥åIJİ
    0.10
    æļĤåģľ
    0.10
    Activations Density 0.447%

    No Known Activations