© 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. 50802
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or punctuation

    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
    æ°Ľ
    -0.07
    æ²³éķĩ
    -0.07
    ême
    -0.07
    วัà¸Ĵà¸Ļ
    -0.07
    ault
    -0.07
    वार
    -0.07
    tert
    -0.06
    ChangedEventArgs
    -0.06
    ä¸ŃåIJ«
    -0.06
    åİī
    -0.06
    POSITIVE LOGITS
    UTO
    0.09
    emens
    0.08
    æķ°åĢ¼
    0.07
    ypi
    0.07
    engel
    0.07
    ackson
    0.07
    ainless
    0.07
    uto
    0.07
     pronounced
    0.07
    åĢ¼
    0.07
    Activations Density 0.068%

    No Known Activations