© 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. 31586
    Prev
    Next
    INDEX
    Explanations

    equilibrium and periodic points

    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
    .parts
    -0.07
    .setWindowTitle
    -0.07
    _acquire
    -0.07
    ffield
    -0.07
    lÄħ
    -0.07
    ç²¾èī¯
    -0.07
    é«ĺåľ°
    -0.07
    aglia
    -0.07
    æ°´åĻ¨
    -0.07
     Temb
    -0.07
    POSITIVE LOGITS
     stability
    0.09
    çļĦåŃĺåľ¨
    0.08
    æģ¯
    0.08
     Stability
    0.08
     stable
    0.08
    稳å®ļæĢ§
    0.08
    稳
    0.08
    stable
    0.07
     solitary
    0.07
    åŃĺåľ¨çļĦ
    0.07
    Activations Density 0.006%

    No Known Activations