© 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. 21661
    Prev
    Next
    INDEX
    Explanations

    oscillations and variations

    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
     szemp
    -0.07
    èįīåľ°
    -0.07
    åįĥéĩĮ
    -0.07
    漫éķ¿
    -0.07
    åį·
    -0.07
    åIJĿ
    -0.07
    æĽ´éķ¿
    -0.07
    νοÏį
    -0.07
    롬
    -0.06
    pace
    -0.06
    POSITIVE LOGITS
     fluctuations
    0.12
     ±
    0.11
     fluct
    0.11
    èµ·ä¼ı
    0.11
     deviations
    0.10
     +/-
    0.10
     variation
    0.10
    åĽ´ç»ķçĿĢ
    0.10
    æ³¢åĬ¨
    0.10
    ä¸Ĭä¸ĭ
    0.10
    Activations Density 0.079%

    No Known Activations