© 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. 46233
    Prev
    Next
    INDEX
    Explanations

    cyclic sweep and hysteresis

    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
     головÑĭ
    -0.07
    elos
    -0.07
    dil
    -0.07
    åıĹéĻIJ
    -0.06
    ä¸īåĽ½
    -0.06
    姿
    -0.06
    atars
    -0.06
    åĿĩè¡¡
    -0.06
    平价
    -0.06
    ww
    -0.06
    POSITIVE LOGITS
    cycle
    0.10
    Cycle
    0.09
     cycle
    0.09
    åĽŀæĿ¥
    0.08
    次åĽŀ
    0.08
    åĽŀæĿ¥äºĨ
    0.08
    zig
    0.08
    -cycle
    0.08
    åĽŀæĿ¥çļĦ
    0.08
    iette
    0.08
    Activations Density 0.008%

    No Known Activations