© 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. 24706
    Prev
    Next
    INDEX
    Explanations

    budget buys

    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
    дÑĢ
    -0.08
    ::__
    -0.07
    resto
    -0.07
    ãģ¨ãģĵãĤįãģ§
    -0.07
    鸳
    -0.07
     Hood
    -0.07
    Ỽm
    -0.07
    èĥ¤
    -0.07
    attore
    -0.06
    åĮºéķ¿
    -0.06
    POSITIVE LOGITS
    åĵªäºĽ
    0.10
    å¤ļéĢīé¢ĺ
    0.09
    æľīåĵªäºĽ
    0.08
    å¤ļéĢī
    0.08
    转è§Ĵ
    0.08
    éģĩ
    0.08
    stav
    0.07
    озна
    0.07
    åijĬ
    0.07
    åĵªäºĽæĸ¹éĿ¢
    0.07
    Activations Density 0.001%

    No Known Activations