© 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. 65290
    Prev
    Next
    INDEX
    Explanations

    package 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
    /flutter
    -0.10
    ocu
    -0.07
    è¿ĩç¥ŀ
    -0.07
    italia
    -0.07
    /owl
    -0.07
    Binder
    -0.07
    flutter
    -0.07
    å¹³çļĦ
    -0.07
    omic
    -0.07
    Ŀ¼
    -0.07
    POSITIVE LOGITS
     contrib
    0.07
     standalone
    0.07
     optional
    0.07
    缮
    0.07
    .compat
    0.07
    оÑģÑĤи
    0.07
    daemon
    0.06
    asilan
    0.06
    å°ĶåŁº
    0.06
    @@
    0.06
    Activations Density 0.103%

    No Known Activations