© 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. 46587
    Prev
    Next
    INDEX
    Explanations

    legal cases and enforcement

    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
    _checker
    -0.07
    amas
    -0.07
    èѦæĪĴ
    -0.07
    subscribe
    -0.07
     obed
    -0.07
    æģĴ
    -0.07
    转载请
    -0.07
    æģĴå®ļ
    -0.07
    éĵº
    -0.07
     momentarily
    -0.06
    POSITIVE LOGITS
     recourse
    0.10
    æıIJèµ·
    0.10
    ä¿ĿæĬ¤èĩªå·±çļĦ
    0.10
    éĢĶå¾Ħ
    0.09
    èµ·è¯ī
    0.09
     pursue
    0.09
    ç»´æĿĥ
    0.09
     damages
    0.09
     pursuit
    0.09
     pursuing
    0.09
    Activations Density 0.092%

    No Known Activations