© 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. 40193
    Prev
    Next
    INDEX
    Explanations

    if...non-

    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
    soever
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    illet
    -0.08
    สà¹Į
    -0.08
    gether
    -0.07
    æĥķ
    -0.07
    ../../../
    -0.07
    为æŃ¢
    -0.07
    ï¸ı
    -0.07
    la
    -0.07
    POSITIVE LOGITS
    è¯ļåĭ¿æī°
    0.12
    bies
    0.10
    ÑĢед
    0.08
    actory
    0.08
    landers
    0.08
    ONTAL
    0.08
    uentes
    0.08
    ivol
    0.07
    ington
    0.07
    loating
    0.07
    Activations Density 0.002%

    No Known Activations