© 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. 39666
    Prev
    Next
    INDEX
    Explanations

    pressure changes

    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
    imir
    -0.07
    æŃ»ä¸į
    -0.07
    æĮ¯åįİ
    -0.07
    _chain
    -0.07
     chain
    -0.07
    çĩİ
    -0.07
    ä¼ĺ
    -0.07
     Composition
    -0.07
    ä¼ĺåĮĸ
    -0.07
    åĨ»
    -0.07
    POSITIVE LOGITS
    çļĦåİŁçIJĨ
    0.09
    æµģéĢŁ
    0.09
    èIJ¥éĢłäºĨ
    0.09
    åİŁçIJĨ
    0.08
    产çĶŁäºĨ
    0.08
     creates
    0.08
    æīģæ¡ĥ
    0.08
    creates
    0.08
     Creates
    0.07
    çļĦ产çĶŁ
    0.07
    Activations Density 0.011%

    No Known Activations