© 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. 55932
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and games

    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
    ioned
    -0.08
    onet
    -0.07
    inach
    -0.07
    æľīçļĦæĺ¯
    -0.07
    bon
    -0.06
    iron
    -0.06
    iona
    -0.06
    ä¸ĢçĽ´ä»¥
    -0.06
    ions
    -0.06
    Scrollbar
    -0.06
    POSITIVE LOGITS
    YPE
    0.07
    anghai
    0.07
     Snyder
    0.07
    _PREF
    0.07
    èĮĥåĽ´çļĦ
    0.07
    çļĦå¤ľæĻļ
    0.07
    igan
    0.07
     gang
    0.06
    uke
    0.06
    ä¸īæĹ¥
    0.06
    Activations Density 0.001%

    No Known Activations