© 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. 12088
    Prev
    Next
    INDEX
    Explanations

    current status or future state

    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
     recent
    -0.09
    æľĢè¿ij
    -0.08
    recent
    -0.08
    容æĺĵå¼ķèµ·
    -0.07
    è¿ijå¹´æĿ¥
    -0.07
     recently
    -0.07
    ...
    -0.07
    è¿ijå¹´
    -0.07
     Recent
    -0.07
    è¿ijæľŁ
    -0.06
    POSITIVE LOGITS
    ä¸įåĨįæľī
    0.13
    ä¸įä¼ļåĨį
    0.13
     оконÑĩаÑĤелÑĮно
    0.13
     artık
    0.13
     ÏĢλÎŃον
    0.12
    åĨįä¹Ł
    0.11
    åĨįä¹Łä¸į
    0.11
    ä¹Łä¸įåĨį
    0.11
    åĨįä¹Łæ²¡æľī
    0.11
    è¿ĻæŶçļĦ
    0.11
    Activations Density 0.142%

    No Known Activations