© 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. 30726
    Prev
    Next
    INDEX
    Explanations

    quantifiers and mathematical terms

    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
    带åĬ¨ä¸ĭ
    -0.07
    ä½ľåĪĻ
    -0.07
    çu
    -0.07
     Traditional
    -0.06
     traditional
    -0.06
    ç¶ĵ
    -0.06
    è¦ģæ±Ĥèĩªå·±
    -0.06
    æĿ¥éĻ¢
    -0.06
    çİĦæѦ
    -0.06
    traditional
    -0.06
    POSITIVE LOGITS
    羡
    0.09
    abee
    0.08
    oken
    0.08
    asics
    0.08
    /fw
    0.08
    antis
    0.07
    åIJĮ士
    0.07
    inker
    0.07
    oriously
    0.07
    çĭ¬è§Ĵ
    0.07
    Activations Density 0.024%

    No Known Activations