© 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. 50299
    Prev
    Next
    INDEX
    Explanations

    syndromes, pathogens, kind

    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
    .setdefault
    -0.07
    ç§ijåѦ
    -0.07
     equ
    -0.07
    åķĨ
    -0.07
    æľīæķĪ
    -0.07
    chas
    -0.06
    ä¼ĺç¾İ
    -0.06
    æľī天
    -0.06
    å®Ī
    -0.06
     ÑįÑĦÑĦекÑĤивнÑĭм
    -0.06
    POSITIVE LOGITS
    å«Įçĸij
    0.10
    åı¯èĥ½æĢ§
    0.10
    ä¹Łåı¯èĥ½æĺ¯
    0.09
    ache
    0.09
    çļĦåı¯èĥ½æĢ§
    0.09
    æľīåı¯èĥ½æĺ¯
    0.08
     possibilities
    0.08
     identifiable
    0.08
    çļĦ迹象
    0.08
     possibility
    0.08
    Activations Density 0.065%

    No Known Activations