© 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. 48016
    Prev
    Next
    INDEX
    Explanations

    code punctuation prefixes

    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
    езд
    -0.07
    ensee
    -0.07
    uta
    -0.07
    ะ
    -0.07
     kabar
    -0.07
    ä¹ĭéŃĤ
    -0.07
    _ALL
    -0.06
     Att
    -0.06
     All
    -0.06
    辫
    -0.06
    POSITIVE LOGITS
    åĪ«æĹł
    0.07
    cott
    0.07
    éĻIJ
    0.07
    æľīå¿ħè¦ģ
    0.06
    :frame
    0.06
     bel
    0.06
    éľįå°Ķ
    0.06
    éĤ
    0.06
    éĻĮ
    0.06
    误ä¼ļ
    0.06
    Activations Density 0.002%

    No Known Activations