© 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. 26595
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     Sle
    -0.08
    elig
    -0.07
    #/
    -0.07
    lier
    -0.07
    åį¡ç½Ĺ
    -0.07
    log
    -0.06
    ::$
    -0.06
     prior
    -0.06
    $/
    -0.06
    åĩłä½į
    -0.06
    POSITIVE LOGITS
    znÄĽ
    0.08
    quem
    0.08
    ÙĪÙĨس
    0.07
    åĴĮåĪ«äºº
    0.07
     minuta
    0.07
    orque
    0.07
    rosoft
    0.07
    æĹłçĹĽäººæµģ
    0.07
     begr
    0.07
    å±ħé«ĺ
    0.07
    Activations Density 0.001%

    No Known Activations