© 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. 51636
    Prev
    Next
    INDEX
    Explanations

    back and forth movement or cycles

    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
    azzi
    -0.09
    äºīä¼ĺ
    -0.07
    é»ĺ认æİĴåºı
    -0.07
    åľ¨è¿Ļåľº
    -0.07
    åİĭåĢĴ
    -0.07
    妥妥
    -0.07
    ä½İä¸ĭ头
    -0.07
    initi
    -0.07
    æĹłå¤Ħ
    -0.07
     diversion
    -0.07
    POSITIVE LOGITS
    äº¤æĽ¿
    0.18
     alternating
    0.16
     altern
    0.15
    å¾Ģå¤į
    0.15
     cycles
    0.15
    è¿Ľåĩº
    0.14
    å¾Ģè¿Ķ
    0.14
    åıįå¤į
    0.14
     fluct
    0.14
     cycle
    0.14
    Activations Density 0.194%

    No Known Activations