© 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. 34497
    Prev
    Next
    INDEX
    Explanations

    Field of the Invention

    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
    otime
    -0.08
    é¦Ĵ头
    -0.08
    UDE
    -0.08
    udas
    -0.08
    umos
    -0.08
    apul
    -0.08
    amna
    -0.08
    ymous
    -0.08
    allet
    -0.08
    æĪ´ç»´æĸ¯
    -0.07
    POSITIVE LOGITS
    Rev
    0.06
    æľ¬èº«
    0.06
     per
    0.06
    ose
    0.06
    uppy
    0.05
     b
    0.05
     level
    0.05
    b
    0.05
     ed
    0.05
     %(
    0.05
    Activations Density 0.032%

    No Known Activations