© 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. 49320
    Prev
    Next
    INDEX
    Explanations

    .py" file extensions

    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
     outr
    -0.09
    lipp
    -0.08
    çľ¼çļ®
    -0.07
    Untitled
    -0.07
     بعÙĨÙĪاÙĨ
    -0.07
    estan
    -0.07
    esty
    -0.07
    acco
    -0.07
    å¹Į
    -0.07
    ФÐĺ
    -0.07
    POSITIVE LOGITS
    å±Ģ
    0.07
    æĿ¥è¯´
    0.06
    iga
    0.06
    åĽ¢
    0.06
    alog
    0.06
    ä¹į
    0.06
    åħ¬
    0.06
    幡
    0.06
     waived
    0.06
     Shea
    0.06
    Activations Density 0.643%

    No Known Activations