© 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. 55286
    Prev
    Next
    INDEX
    Explanations

    list items or dictionary entries

    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
    arjo
    -0.08
    åĬ²
    -0.07
    __((
    -0.07
    ÑĤÑĮе
    -0.07
    nown
    -0.07
    astien
    -0.06
    åįķè¾¹
    -0.06
    å±ĤéĿ¢ä¸Ĭ
    -0.06
    åĽ¢åĽ¢
    -0.06
    iffin
    -0.06
    POSITIVE LOGITS
    èĭŀ
    0.07
    æľīçļĦ人
    0.07
    ï¸İ
    0.06
    itik
    0.06
    -package
    0.06
    haul
    0.06
    æĪijè¦ģæĬķè¯ī
    0.06
    ÙĪÙĨا
    0.06
    ái
    0.06
    ises
    0.06
    Activations Density 0.018%

    No Known Activations