© 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. 23530
    Prev
    Next
    INDEX
    Explanations

    theory and technical terms

    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
    łíĮ
    -0.10
    íĥ
    -0.08
     cris
    -0.08
    /DD
    -0.08
    estia
    -0.08
    缴æİ¥æĪĸéĹ´æİ¥
    -0.08
    èģļåĬĽ
    -0.07
    åŁĭåľ¨
    -0.07
    мÑı
    -0.07
    cco
    -0.07
    POSITIVE LOGITS
     technically
    0.09
     technical
    0.08
    æĬĢæľ¯ä¸Ĭ
    0.08
    oret
    0.08
     Technical
    0.08
    technical
    0.07
    åѤ
    0.07
    æĬĢæľ¯æĢ§
    0.07
    åį·
    0.07
     mathematics
    0.07
    Activations Density 0.043%

    No Known Activations