© 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. 65369
    Prev
    Next
    INDEX
    Explanations

    sentence-ending 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
    oute
    -0.10
    éŀĭ帽
    -0.09
    ØŃاÙĦ
    -0.08
    arbon
    -0.08
    ostar
    -0.08
    azer
    -0.08
    ä¸īå®Ŀ
    -0.08
    andre
    -0.08
    缸éļı
    -0.08
    lite
    -0.07
    POSITIVE LOGITS
    ...
    0.06
     dot
    0.06
    æĥ³è±¡
    0.06
    iem
    0.06
    _TLS
    0.05
     imagin
    0.05
    çĽĬ
    0.05
     sa
    0.05
    æĥ³åĥı
    0.05
    วà¹Īา
    0.05
    Activations Density 0.001%

    No Known Activations