© 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. 30687
    Prev
    Next
    INDEX
    Explanations

    programming code delimiters

    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
    大æŀĹ
    -0.08
    æ§Ľ
    -0.07
    å°±ç®ĹäºĨ
    -0.07
    æī¬éķ¿
    -0.07
    ulli
    -0.07
    .capitalize
    -0.07
     Dana
    -0.07
     suspend
    -0.07
    ä¸Ģå¹´æĿ¥
    -0.06
    HttpClient
    -0.06
    POSITIVE LOGITS
    _safe
    0.08
    æĸĩ
    0.07
    -parse
    0.07
    ìļ±
    0.07
    -next
    0.07
    ESTAMP
    0.07
    ç¯Ģ
    0.07
    èĦĤ
    0.07
    æ¯Ĵ
    0.07
    ested
    0.07
    Activations Density 0.005%

    No Known Activations