© 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. 57924
    Prev
    Next
    INDEX
    Explanations

    first describes

    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
    zyw
    -0.08
    اÙĦÙī
    -0.08
    åŃĹçľ¼
    -0.07
    æ»ŀ纳
    -0.07
    /generated
    -0.07
    dade
    -0.07
     additionally
    -0.07
    éĿĴéĿĴ
    -0.07
     ulterior
    -0.07
     huel
    -0.07
    POSITIVE LOGITS
     foundational
    0.08
     general
    0.08
     basics
    0.08
     basic
    0.08
    æĢ»ä½ĵè¦ģæ±Ĥ
    0.07
    just
    0.07
     Grundlagen
    0.07
    åŁºæľ¬ä¿¡æģ¯
    0.07
    éĢļåĪĻ
    0.07
     broad
    0.07
    Activations Density 0.010%

    No Known Activations