© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15172
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    λαν
    -0.07
    во
    -0.07
    ulich
    -0.07
    ÑīеÑĤ
    -0.07
    ä¸Ģ路走æĿ¥
    -0.07
     bunny
    -0.06
    villa
    -0.06
     dispositiv
    -0.06
    èį·
    -0.06
    chè
    -0.06
    POSITIVE LOGITS
    tape
    0.09
    achim
    0.08
     Tape
    0.08
    CEED
    0.07
    æľĢåħ·
    0.07
    satz
    0.07
    į¨
    0.07
    æĭ©
    0.07
     zgod
    0.07
    este
    0.07
    Activations Density 0.005%

    No Known Activations