© 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. 25219
    Prev
    Next
    INDEX
    Explanations

    mathematical questions using is

    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
    åĴĮæ°Ķ
    -0.09
    icus
    -0.08
    stuhl
    -0.07
    ÏĥÏĦη
    -0.07
    itte
    -0.07
    ovski
    -0.07
    äºİè¡Į
    -0.07
    io
    -0.07
    efs
    -0.07
    stät
    -0.07
    POSITIVE LOGITS
    ellik
    0.07
    åľı
    0.06
    apl
    0.06
    禦
    0.06
    coc
    0.06
    âĹ¯
    0.06
    çĪĨäºĨ
    0.06
    íķ©
    0.06
    berra
    0.06
    Thrown
    0.06
    Activations Density 0.051%

    No Known Activations