© 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. 29606
    Prev
    Next
    INDEX
    Explanations

    numbers one, 1

    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
    lau
    -0.09
    elow
    -0.08
    udin
    -0.08
    amt
    -0.08
    ستاÙĨ
    -0.08
    ligen
    -0.08
    ষà§įà¦Ł
    -0.08
    è·Ŀä»Ĭ
    -0.07
    ız
    -0.07
    é«ĺæĸ¼
    -0.07
    POSITIVE LOGITS
    ish
    0.08
    ä¸Ķ
    0.07
    ä¸Ķæľī
    0.06
    imensional
    0.06
    èĨ¨èĥĢ
    0.06
    rou
    0.06
    ibo
    0.06
    å¼Ħ
    0.06
    ÙĬاÙĦ
    0.05
     multiples
    0.05
    Activations Density 0.003%

    No Known Activations