© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21578
    Prev
    Next
    INDEX
    Explanations

    code syntax and punctuation

    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
    oles
    -0.07
    Ïģθ
    -0.06
    æĺ
    -0.06
    wer
    -0.06
    æĽ
    -0.06
    .uk
    -0.06
    éĽ¾
    -0.06
    ticks
    -0.06
    åıĽ
    -0.06
    à¸Ľà¸£
    -0.06
    POSITIVE LOGITS
    entu
    0.09
    俱ä¹IJéĥ¨
    0.08
    åĬĽæīĢèĥ½åıĬ
    0.08
    æľīè¯Ŀ
    0.07
    ä¸įçĶ±
    0.07
    代è¡Į
    0.07
    ëį°ë¯¸
    0.07
    INET
    0.07
    kün
    0.07
    integration
    0.07
    Activations Density 0.004%

    No Known Activations