© 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. 24997
    Prev
    Next
    INDEX
    Explanations

    steady-state equilibrium

    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
    人ä¸Ń
    -0.09
    KeyId
    -0.09
    -Za
    -0.08
    éĽ¨éľ²
    -0.08
    çĻ½çļĻ
    -0.08
    erty
    -0.08
    责任åįķä½į
    -0.08
    åij½ä¸Ńçİĩ
    -0.08
    æĻºèĥ½ç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.08
    Åijr
    -0.07
    POSITIVE LOGITS
    stable
    0.10
    稳å®ļçļĦ
    0.10
    /static
    0.09
     stable
    0.09
    稳å®ļ
    0.09
    éĿĻæĢģ
    0.09
    steady
    0.08
     stability
    0.08
     steady
    0.08
    ä¹ħ
    0.08
    Activations Density 0.011%

    No Known Activations