© 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. 44925
    Prev
    Next
    INDEX
    Explanations

    score results

    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
    rh
    -0.07
    天ä¸ĬçļĦ
    -0.07
    olla
    -0.07
     Dul
    -0.06
    rw
    -0.06
    åIJİæĦŁ
    -0.06
    ase
    -0.06
    æĸĩåĮĸä¼łåªĴæľīéĻIJåħ¬åı¸
    -0.06
    SetActive
    -0.06
     ×Ĺ×Ļ
    -0.06
    POSITIVE LOGITS
    abis
    0.08
    ×ĵ×Ļ×Ŀ
    0.08
    åħ
    0.07
    éĻ¤ä»¥
    0.07
    å¦
    0.07
    à¸ĩ
    0.07
     ÙĪجÙĩ
    0.07
    ÙĪجÙĩ
    0.07
     огне
    0.07
    çİĽ
    0.07
    Activations Density 0.157%

    No Known Activations