© 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. 49769
    Prev
    Next
    INDEX
    Explanations

    and followed by names

    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
    âu
    -0.08
    é£İéĻ©åĴĮ
    -0.08
    kons
    -0.07
    ÏĪη
    -0.07
    åİĭåĬĽåĴĮ
    -0.07
    èĩ´è¿ľ
    -0.07
    å®īåħ¨æĢ§åĴĮ
    -0.07
    大çĹħ
    -0.07
    ãģĵãģ¨ãĤĦ
    -0.07
    izen
    -0.07
    POSITIVE LOGITS
    ])==
    0.07
    icule
    0.07
    olk
    0.06
    æĸ°åĬłåĿ¡
    0.06
    lify
    0.06
    åIJĮæł·
    0.06
    ='-
    0.06
    ifice
    0.06
    å¦ĩ
    0.06
     kern
    0.06
    Activations Density 0.041%

    No Known Activations