© 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. 41203
    Prev
    Next
    INDEX
    Explanations

    output logs

    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
    /native
    -0.08
    ness
    -0.08
     اÙĦÙĨÙģ
    -0.08
    è¯Ńè¨Ģ表达èĥ½åĬĽ
    -0.07
    NESS
    -0.07
    ights
    -0.07
    à¹Ĩ
    -0.07
    eman
    -0.07
    ighb
    -0.07
    اÛĮت
    -0.07
    POSITIVE LOGITS
    ting
    0.11
    åĴĮæݨ广
    0.09
    åĴĮçłĶ究
    0.07
    elman
    0.07
    ize
    0.07
    ugg
    0.07
    满满
    0.07
    a
    0.07
    izzo
    0.07
    åĴĮæĢĿèĢĥ
    0.07
    Activations Density 0.004%

    No Known Activations