© 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. 12365
    Prev
    Next
    INDEX
    Explanations

    object reference

    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
    ;base
    -0.08
    éĢļçĶ¨
    -0.07
    éĢļçĶ¨çļĦ
    -0.07
    anz
    -0.07
     numerical
    -0.07
    åıĸèĩª
    -0.07
    å¿ħéľĢåĵģ
    -0.07
    éĿĴæĿ¾
    -0.07
    ä¸İç»´ä¿®
    -0.07
    ä¼ģä¸ļè¿Ľè¡Į
    -0.06
    POSITIVE LOGITS
    uide
    0.08
    åħ³ç³»
    0.07
    _SPECIAL
    0.07
    æľ¬èº«
    0.07
    voi
    0.07
    .mark
    0.07
    Authenticated
    0.07
    occo
    0.07
    èݽ
    0.07
    agle
    0.07
    Activations Density 0.021%

    No Known Activations