© 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. 43648
    Prev
    Next
    INDEX
    Explanations

    code constructs like .h files

    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
    zwi
    -0.08
     Agenda
    -0.07
    ushima
    -0.07
    ondi
    -0.07
     TResult
    -0.07
    æ´ŀå¯ŁåĬĽ
    -0.07
     prist
    -0.07
    红æĸij
    -0.07
    ηγ
    -0.07
    _errno
    -0.07
    POSITIVE LOGITS
    represented
    0.08
    对åºĶçļĦ
    0.07
     represented
    0.07
    åħĮ
    0.07
     textual
    0.07
    aps
    0.06
    ass
    0.06
    çŃ¾ç«ł
    0.06
    éĢ
    0.06
    åĩīäºĨ
    0.06
    Activations Density 0.435%

    No Known Activations