© 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. 64356
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code

    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
    schau
    -0.08
    jaman
    -0.08
    åįĬ个å°ıæŶ
    -0.08
    éĴ£
    -0.08
    onte
    -0.07
    èĮĥåĽ´å¹¿
    -0.07
    大æ¦Ĥ
    -0.07
     koronav
    -0.07
    probably
    -0.07
    袴
    -0.07
    POSITIVE LOGITS
    ׳×Ĵ
    0.07
    åĸ³
    0.07
    tock
    0.06
    -divider
    0.06
     discrepancy
    0.06
    uwe
    0.06
     intriguing
    0.06
    çļĦæīĢæľīä½ľåĵģ
    0.06
    度
    0.06
    èģ·
    0.05
    Activations Density 0.016%

    No Known Activations