© 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. 10926
    Prev
    Next
    INDEX
    Explanations

    commutation

    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
    ests
    -0.08
    entie
    -0.07
     positional
    -0.07
    éĩıçļĦ
    -0.07
    ä¸Ńå¿ĥåĮĸ
    -0.07
    _os
    -0.06
    tros
    -0.06
    osh
    -0.06
    ä¸Ńå¿ĥçļĦ
    -0.06
    ä¸Ģ举
    -0.06
    POSITIVE LOGITS
    -region
    0.10
     region
    0.09
     continuity
    0.09
    第äºĮ段
    0.09
    åĮºåŁŁ
    0.09
    åĮºåĨħ
    0.09
     Segment
    0.09
    Region
    0.09
    åĮºåŁŁçļĦ
    0.09
    åĪĨ段
    0.08
    Activations Density 0.026%

    No Known Activations