© 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. 64988
    Prev
    Next
    INDEX
    Explanations

    activations followed by parenthesis

    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
    __
    -0.07
    纤维
    -0.06
    kot
    -0.06
    èĤ¡
    -0.06
     *«
    -0.06
    eva
    -0.06
    gle
    -0.06
     Hip
    -0.06
    sir
    -0.06
    ä¹Łä¸įåı¯èĥ½
    -0.06
    POSITIVE LOGITS
    äºijå³°
    0.09
    ç®Ģ称
    0.08
    èĭ±æĸĩåIJįåŃĹ
    0.08
     ($)
    0.07
     ($.
    0.07
    arest
    0.07
    簡稱
    0.07
    매
    0.07
    .wrapper
    0.07
    ocop
    0.07
    Activations Density 0.199%

    No Known Activations