© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17448
    Prev
    Next
    INDEX
    Explanations

    form of, type of

    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
    umul
    -0.07
    åĪĩå®ŀç»´æĬ¤
    -0.07
    æ
    -0.06
     Tribune
    -0.06
    çĤ³
    -0.06
    alian
    -0.06
    ä½ľä¸ºä¸Ģ个
    -0.06
    å¸ĿåĽ½çļĦ
    -0.06
    çļĦä¸ĢäºĽ
    -0.06
    cios
    -0.06
    POSITIVE LOGITS
    ä¸Ģ種
    0.10
    广ä¹ī
    0.10
    ä¸Ģç§į
    0.10
    åıĺ缸
    0.09
    æĺ¯ä¸Ģç§į
    0.09
     ÑĢазновид
    0.09
    çļĦä¸Ģç§į
    0.09
    ä¹Łæĺ¯ä¸Ģç§į
    0.08
     ÑĢазновидноÑģÑĤи
    0.08
    .kind
    0.08
    Activations Density 0.112%

    No Known Activations