© 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. 28603
    Prev
    Next
    INDEX
    Explanations

    local time

    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
    á»ģm
    -0.07
    ilson
    -0.06
    èĮ¹
    -0.06
    æīĢåįł
    -0.06
    æĴij
    -0.06
    èĥ¡æ¡ĥ
    -0.06
    æģ°æģ°
    -0.06
    å½¢æĪIJäºĨä¸Ģ个
    -0.06
    —which
    -0.06
    itz
    -0.06
    POSITIVE LOGITS
    ê¼
    0.08
    plib
    0.07
    æ¡ĤåĨł
    0.07
     überall
    0.07
    ÙĬاÙĨ
    0.07
    urez
    0.07
    alore
    0.07
    åħ³éĹŃçªĹåı£
    0.07
    æľĢ好æĺ¯
    0.07
    çļĦå¥½ä¹łæĥ¯
    0.07
    Activations Density 0.004%

    No Known Activations