© 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. 20133
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and expressions

    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
    otin
    -0.07
    lix
    -0.07
    erty
    -0.07
    lic
    -0.06
    ayer
    -0.06
     anders
    -0.06
    εί
    -0.06
    st
    -0.06
    ç»ĨåĪĻ
    -0.06
    ay
    -0.06
    POSITIVE LOGITS
    ricos
    0.10
    usercontent
    0.09
    订éĺħä¸ĵæłı
    0.08
    quê
    0.08
    æĽ´æĸ°äºİ
    0.08
    ä»Ģä¹Īåij¢
    0.07
    [url
    0.07
    äºĶæĹ¥
    0.07
     kob
    0.07
    [opt
    0.07
    Activations Density 0.009%

    No Known Activations