© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16205
    Prev
    Next
    INDEX
    Explanations

    Lyapunov exponents

    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
    èĽ
    -0.07
     Achie
    -0.07
     DAT
    -0.07
    Readable
    -0.07
     underage
    -0.07
    åĪĨæľŁ
    -0.07
    ilog
    -0.06
     listing
    -0.06
    DAT
    -0.06
     Waste
    -0.06
    POSITIVE LOGITS
     Hitch
    0.08
     Nearby
    0.08
     Einstein
    0.07
    æ¯Ĺ
    0.07
    åĮĹåIJij
    0.07
    篮
    0.07
    èĤī
    0.07
    åĽĽç»´
    0.07
    _PHY
    0.07
    ooke
    0.07
    Activations Density 0.005%

    No Known Activations