© 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. 10709
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and expressions

    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
    &e
    -0.08
    è¿ĻäºĽäºĭ
    -0.08
     ^=
    -0.07
    æ·±åĪ»é¢Ĩä¼ļ
    -0.07
    OFFSET
    -0.07
     Struk
    -0.07
    æį¶
    -0.06
    åı¥åı¥
    -0.06
    éķ¿ç©º
    -0.06
    orthy
    -0.06
    POSITIVE LOGITS
     numerator
    0.10
    )/(
    0.08
    pons
    0.07
    allah
    0.07
     division
    0.07
    ulary
    0.07
    _pickle
    0.07
     Nau
    0.07
     Pref
    0.07
    nance
    0.07
    Activations Density 0.004%

    No Known Activations