© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14811
    Prev
    Next
    INDEX
    Explanations

    time duration or length

    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
    áva
    -0.09
    æ¸ħç®Ĺä¿¡æģ¯
    -0.08
    æ¯ıç§Ĵ
    -0.08
     desag
    -0.08
    ibur
    -0.08
    äºĶèĬ±
    -0.08
    è°Īç¬ij
    -0.08
    æĺİæĹ¥
    -0.08
     سÙı
    -0.08
    iaux
    -0.07
    POSITIVE LOGITS
     elapsed
    0.13
     longest
    0.12
    累积
    0.11
    è¶Ĭéķ¿
    0.11
    æľĢéķ¿
    0.11
    累计
    0.11
     accumulated
    0.11
    éķ¿çŁŃ
    0.10
    æľĢéķ¿çļĦ
    0.10
    ä¹ĭä¹ħ
    0.10
    Activations Density 0.275%

    No Known Activations