© 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. 3535
    Prev
    Next
    INDEX
    Explanations

    assigning variables

    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
    ׼×ķת
    -0.09
    ennes
    -0.08
    apiro
    -0.08
    atoi
    -0.08
    URITY
    -0.07
    bounce
    -0.07
    IMUM
    -0.07
    Preview
    -0.07
    æļ´é£İ
    -0.07
    {}]
    -0.07
    POSITIVE LOGITS
    chy
    0.07
     vele
    0.07
    æĿ¿ä¸Ĭ
    0.07
    æĪij们认为
    0.07
    jarah
    0.06
    èĭijå°ıåĮº
    0.06
    odb
    0.06
    áĥĹ
    0.06
    lich
    0.06
    æIJŃ
    0.06
    Activations Density 0.040%

    No Known Activations