© 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. 3018
    Prev
    Next
    INDEX
    Explanations

    words ending with 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
    åį³
    -0.07
    ׼ף
    -0.06
     hal
    -0.06
    纪
    -0.06
     ÛĮعÙĨÛĮ
    -0.06
     eli
    -0.06
    hint
    -0.06
    ä¹Łå°±æĺ¯
    -0.06
    ikt
    -0.06
    åİī
    -0.05
    POSITIVE LOGITS
    åĽ½å®¶ä¸Ģ级
    0.09
    adou
    0.09
    arton
    0.08
    sted
    0.08
    è¿Ļæł·çļĦè¯Ŀ
    0.08
    عة
    0.08
    stead
    0.08
    Ø«Ùħ
    0.08
    åı¯æ¢¦
    0.08
    çĦ¶åIJİçĶ¨
    0.08
    Activations Density 0.017%

    No Known Activations