© 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. 2210
    Prev
    Next
    INDEX
    Explanations

    describes the

    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
    frage
    -0.08
    aup
    -0.07
     ÙĤÙĪÙĦÙĩ
    -0.06
     ÏĦί
    -0.06
    imps
    -0.06
    ä¹ĭåIJį
    -0.06
    æĪĸå°ij
    -0.06
    questions
    -0.06
    nop
    -0.06
    dd
    -0.06
    POSITIVE LOGITS
     procedure
    0.09
     how
    0.09
    rocess
    0.09
    è¿Ļ个è¿ĩç¨ĭ
    0.08
     process
    0.08
     ways
    0.08
    æĵįä½ľæµģç¨ĭ
    0.08
     processes
    0.08
    how
    0.08
    å·¥ä½ľæµģç¨ĭ
    0.08
    Activations Density 0.194%

    No Known Activations