© 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. 27175
    Prev
    Next
    INDEX
    Explanations

    math expressions with powers and fractions

    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
    endela
    -0.06
    æĴij
    -0.06
    IRST
    -0.06
    &E
    -0.06
    æīĵèµ·
    -0.06
     fou
    -0.06
    irma
    -0.06
    æĶ¶
    -0.06
    setUp
    -0.06
    ening
    -0.06
    POSITIVE LOGITS
    uber
    0.07
    odia
    0.07
    ÙĪاÙĨ
    0.07
    TAB
    0.07
    DMETHOD
    0.07
    odb
    0.06
    Mix
    0.06
    (scroll
    0.06
    idx
    0.06
    auber
    0.06
    Activations Density 0.012%

    No Known Activations