© 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. 58589
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and greek letters

    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
    Ø©
    -0.10
    i
    -0.09
    ing
    -0.09
    Ìģ
    -0.08
    eous
    -0.07
    Ùĭ
    -0.07
    и
    -0.07
     to
    -0.06
    ,
    -0.06
    a
    -0.06
    POSITIVE LOGITS
    ses
    0.11
    nya
    0.11
    à¸Ļาà¸Ļ
    0.10
    tep
    0.10
    venes
    0.09
    terra
    0.09
    jenigen
    0.09
    à¸Ļิ
    0.09
    ä»ĸåij½
    0.09
    anh
    0.09
    Activations Density 0.078%

    No Known Activations