© 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. 61000
    Prev
    Next
    INDEX
    Explanations

    sequential stages or parts

    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
    oni
    -0.08
    CHA
    -0.08
     εξα
    -0.07
    abu
    -0.07
    uage
    -0.07
    abia
    -0.07
    å¹³éĺ³
    -0.07
     tuh
    -0.07
    igan
    -0.07
    _parsed
    -0.07
    POSITIVE LOGITS
    æ¯ıä¸ĢæŃ¥
    0.15
     sequentially
    0.13
    ä¾Ŀ次
    0.13
     sequential
    0.12
     successive
    0.12
    åIJĦçݯèĬĤ
    0.11
     stages
    0.11
     Sequential
    0.11
    Sequential
    0.11
    sequential
    0.11
    Activations Density 0.187%

    No Known Activations