© 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. 26616
    Prev
    Next
    INDEX
    Explanations

    greek letters in math contexts

    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
    mans
    -0.06
    Ñĩа
    -0.06
    eneg
    -0.06
     swell
    -0.06
    ç¿»
    -0.06
     biased
    -0.06
    è¹
    -0.06
    imizer
    -0.06
    æłijç§į
    -0.06
    åıĪä½ķ
    -0.06
    POSITIVE LOGITS
    —the
    0.08
    baran
    0.07
    åIJĮåŃ¦åľ¨
    0.07
    jš
    0.07
    ç½ĹæĽ¼
    0.07
    åıĶ
    0.07
     kud
    0.07
    —a
    0.07
    icy
    0.07
    个èµŀ
    0.07
    Activations Density 0.064%

    No Known Activations