© 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. 39707
    Prev
    Next
    INDEX
    Explanations

    performance and speed

    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
    æĽ´åĬłæĸ¹ä¾¿
    -0.09
    å¤ļ姿
    -0.08
    祸
    -0.08
    ái
    -0.08
    mbH
    -0.07
     autoFocus
    -0.07
    Filled
    -0.07
    _supply
    -0.07
    же
    -0.07
    ripp
    -0.07
    POSITIVE LOGITS
     CPU
    0.11
     computational
    0.11
     speed
    0.10
     computation
    0.10
     runtime
    0.10
    è¿IJç®Ĺ
    0.10
    CPU
    0.09
     computations
    0.09
     speeds
    0.09
     CPUs
    0.09
    Activations Density 0.272%

    No Known Activations