© 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. 19427
    Prev
    Next
    INDEX
    Explanations

    time and duration

    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
    å½ĵæĻļ
    -0.08
    ãĤĦãģ£ãģ¨
    -0.08
    ä»ĬæĻļ
    -0.08
    _checksum
    -0.08
    ä¸īå¹´æĿ¥
    -0.07
    ãĥĥãĤŃãĥ¼
    -0.07
    ä¸ĢæĹģ
    -0.07
     hex
    -0.07
    ä¸ĭä¸ĢæŃ¥
    -0.07
    ÃŃtÄĽ
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵæŶéĹ´
    0.13
     elapsed
    0.10
    æŶéĹ´çĤ¹
    0.10
    Elapsed
    0.09
    Time
    0.09
    æŶéĹ´çļĦ
    0.09
     time
    0.09
    -time
    0.09
    otime
    0.09
    æŶéĹ´
    0.09
    Activations Density 0.013%

    No Known Activations