© 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. 32993
    Prev
    Next
    INDEX
    Explanations

    orbital energy configurations

    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
    s
    -0.07
    -ever
    -0.07
    俱ä¹IJéĥ¨
    -0.07
    ãĤĪãģĨãģª
    -0.07
    à¹Ĩ
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    ×ķ
    -0.07
    elter
    -0.06
    ese
    -0.06
    edom
    -0.06
    POSITIVE LOGITS
    solete
    0.09
    ity
    0.09
    ÙĬÙĨ
    0.09
    iginal
    0.08
    phan
    0.08
    byname
    0.08
    culated
    0.08
    zicht
    0.08
    orauss
    0.08
    eneuve
    0.08
    Activations Density 0.002%

    No Known Activations