© 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. 46210
    Prev
    Next
    INDEX
    Explanations

    longest, maximum, or specific points

    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
    å¤ļ好
    -0.08
    opan
    -0.08
    æĿ¡å½¢çłģ
    -0.07
     giapp
    -0.07
    æŀĹçĭ¬
    -0.07
    纯åĩĢ
    -0.07
     goodies
    -0.07
    etrie
    -0.07
    æĸ¤
    -0.07
    RAFT
    -0.07
    POSITIVE LOGITS
     worst
    0.13
    æľĢéľĢè¦ģ
    0.13
    æľĢ容æĺĵ
    0.13
    æľĢä¸į
    0.12
    æľĢå·®
    0.12
    wor
    0.12
     Worst
    0.10
    æľĢåĢ¼å¾Ĺ
    0.10
    æľĢéļ¾
    0.10
    æľĢéķ¿çļĦ
    0.10
    Activations Density 0.011%

    No Known Activations