© 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. 1032
    Prev
    Next
    INDEX
    Explanations

    square root or square root type

    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
    交éģĵ
    -0.09
    ìĦĿ
    -0.09
    大æŀĹ
    -0.09
    iria
    -0.08
    夥
    -0.08
     ÙĪسÙĦ
    -0.08
     erfolgre
    -0.08
    eah
    -0.08
    .unregister
    -0.08
    stück
    -0.08
    POSITIVE LOGITS
     of
    0.07
    ::-
    0.06
    angan
    0.06
    ation
    0.06
    夷
    0.06
     (
    0.06
    (s
    0.06
    à¸Ĥà¸Ńà¸ĩà¸Ħวาม
    0.05
     operation
    0.05
    æ¨Ł
    0.05
    Activations Density 0.002%

    No Known Activations