© 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. 50583
    Prev
    Next
    INDEX
    Explanations

    cyclization reactions

    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
    ä¸Ģå¸Ĩé£İ顺
    -0.07
    ä¸įæĮ¯
    -0.07
     ale
    -0.06
     real
    -0.06
     refresh
    -0.06
     inf
    -0.06
     distribu
    -0.06
     thorough
    -0.06
     settled
    -0.06
     sorted
    -0.06
    POSITIVE LOGITS
    èĩªæķij
    0.10
     looping
    0.10
    å½¢æĪIJäºĨä¸Ģ个
    0.09
    å½¢æĪIJä¸Ģ个
    0.09
    è¿ijåľ¨
    0.09
     closure
    0.09
    /self
    0.08
    /Internal
    0.08
    closing
    0.08
    éĸī
    0.08
    Activations Density 0.033%

    No Known Activations