© 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. 51672
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical expressions

    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
    æĴ¼
    -0.07
    æĪĸä¸į
    -0.07
    ãĤ«ãĥł
    -0.07
    åį§
    -0.07
    æľªå®Įå¾ħç»Ń
    -0.07
    ì¡°íķ©
    -0.07
    unken
    -0.07
    ķĮ
    -0.07
    ķħ
    -0.06
    neau
    -0.06
    POSITIVE LOGITS
    cking
    0.07
    osg
    0.07
    Ø·
    0.07
    ç¹°
    0.06
    à¸Ĺา
    0.06
    ingly
    0.06
    uling
    0.06
    à¸
    0.06
     Serg
    0.06
    _taxonomy
    0.06
    Activations Density 0.006%

    No Known Activations