© 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. 57923
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    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
    æĺ¯æĢİä¹Ī
    -0.07
    æĺ¯å¦Ĥä½ķ
    -0.07
    erc
    -0.07
     ots
    -0.07
     sequ
    -0.07
    æ¶Įçİ°
    -0.07
    ÏĩÏİ
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.06
     opd
    -0.06
    ike
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩ
    0.07
    ogl
    0.07
    åĢŁ
    0.07
    Helpers
    0.07
    anguard
    0.07
    åij³ãģ®
    0.07
    кÑĥÑĢо
    0.07
    estu
    0.07
    uyến
    0.06
     Represent
    0.06
    Activations Density 0.005%

    No Known Activations