© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    two separate

    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
    physical
    -0.10
    çľŁäºº
    -0.09
    çī©çIJĨ
    -0.09
     physical
    -0.09
     Physical
    -0.08
    çļĦçī©çIJĨ
    -0.08
     earthly
    -0.08
    è¯Ńè¨ĢæĸĩåŃĹ
    -0.08
    è·¨
    -0.08
     indoors
    -0.07
    POSITIVE LOGITS
    layouts
    0.08
    _idle
    0.08
    ллÑı
    0.08
    综åIJĪæķ´æ²»
    0.07
    ä¸Ńå¥ĸ
    0.07
    è¾¹éĻħ
    0.07
     competit
    0.07
    óp
    0.07
    建ä»ĵ
    0.07
    æīī
    0.07
    Activations Density 0.322%

    No Known Activations