© 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. 25833
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
    ylv
    -0.08
    åİĦ
    -0.08
    ìĿ´íĬ¸
    -0.08
    è¹
    -0.07
    çıį
    -0.07
    anson
    -0.07
    åįĵ
    -0.07
    ç´¢
    -0.07
    ERA
    -0.07
    æ²IJ
    -0.07
    POSITIVE LOGITS
     {?}
    0.08
    áĥ¬
    0.07
    Äija
    0.06
    à¸ĭิ
    0.06
     trec
    0.06
    หั
    0.06
    cide
    0.06
    nä
    0.06
    æµĴ
    0.06
    ://%
    0.06
    Activations Density 0.074%

    No Known Activations