© 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. 64961
    Prev
    Next
    INDEX
    Explanations

    code patterns and miscellaneous 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
     Fle
    -0.08
    ÙĦØ©
    -0.07
    éĿĴ天
    -0.06
    åħ·æľīçĭ¬ç«ĭ
    -0.06
    le
    -0.06
    wer
    -0.06
     Wer
    -0.06
    èĵĿåŃĹ
    -0.06
     *__
    -0.06
     Tav
    -0.06
    POSITIVE LOGITS
    dito
    0.09
    ividi
    0.08
     denomin
    0.08
    acol
    0.07
    俨
    0.07
     simplific
    0.07
    phis
    0.07
    ÛĮÙħاÙĨ
    0.07
    æĭ¬åı·
    0.07
     messy
    0.07
    Activations Density 0.001%

    No Known Activations