© 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. 45168
    Prev
    Next
    INDEX
    Explanations

    list separators and endings

    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
    ï¼Ī
    -0.07
    adoo
    -0.07
     while
    -0.06
    !
    -0.06
    “
    -0.06
    *
    -0.06
    èĢĮ
    -0.06
    ï¼ģï¼Ī
    -0.06
    A
    -0.05
    æĮº
    -0.05
    POSITIVE LOGITS
     etc
    0.14
     ...)
    0.12
    etc
    0.12
     itd
    0.11
     غÙĬرÙĩ
    0.10
     ฯลฯ
    0.09
    âĢ¦)
    0.09
    phans
    0.09
    顾åIJįæĢĿ
    0.09
     _)
    0.09
    Activations Density 0.119%

    No Known Activations