© 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. 15219
    Prev
    Next
    INDEX
    Explanations

    links and code blocks

    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
    yth
    -0.07
    unami
    -0.07
    нг
    -0.07
    imei
    -0.07
    refix
    -0.07
    utie
    -0.07
     '*.
    -0.07
    åī©
    -0.07
    abaya
    -0.07
    éªĮ
    -0.07
    POSITIVE LOGITS
    ago
    0.07
    ä¸īéĿ¢
    0.07
    ä¸ĸçķĮä¸Ģæµģ
    0.07
    itiva
    0.06
    apu
    0.06
    elman
    0.06
    tives
    0.06
    æĴ«
    0.06
    leton
    0.06
     Ton
    0.06
    Activations Density 0.066%

    No Known Activations