© 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. 33719
    Prev
    Next
    INDEX
    Explanations

    quality certification

    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
    èĩªçĦ¶ä¼ļ
    -0.08
    åıĮé±¼
    -0.08
    apos
    -0.08
    æľ¬çıŃ
    -0.08
    യാ
    -0.07
    Å¡an
    -0.07
    ivor
    -0.07
     Internationale
    -0.07
    olulu
    -0.07
    ologÃŃa
    -0.06
    POSITIVE LOGITS
    mente
    0.09
    lle
    0.07
    ylie
    0.06
    ricional
    0.06
    åıĪ称
    0.06
    lex
    0.06
    entially
    0.06
    chers
    0.06
     versus
    0.06
    æıŃ
    0.06
    Activations Density 0.073%

    No Known Activations