© 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. 43366
    Prev
    Next
    INDEX
    Explanations

    components and materials

    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
    кеÑĢ
    -0.08
    abase
    -0.08
    å¾·åŁº
    -0.07
    acol
    -0.07
    åĸľéĹ»
    -0.07
    วม
    -0.07
    yun
    -0.07
    çijŀæĭī
    -0.07
    DP
    -0.07
    ache
    -0.07
    POSITIVE LOGITS
    [s
    0.09
    stwo
    0.09
    ither
    0.07
    Ùĭ
    0.07
    HCI
    0.07
    ÑĬÑĤ
    0.07
    /*@
    0.07
    swith
    0.07
    约èĢĮåIJĮ
    0.07
    笤
    0.07
    Activations Density 1.024%

    No Known Activations