© 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. 39378
    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
    ä¸į足以
    -0.08
    ôi
    -0.07
    adera
    -0.07
    agi
    -0.07
     whereby
    -0.06
    å²±
    -0.06
    kü
    -0.06
     Testament
    -0.06
    ä¹Łå°±æĦıåij³çĿĢ
    -0.06
    hausen
    -0.06
    POSITIVE LOGITS
    为己任
    0.08
     imper
    0.08
     Caranya
    0.08
     caranya
    0.07
    etus
    0.07
    å¿ħä¸įåı¯å°ij
    0.07
    为å®ĹæŨ
    0.07
    ä¸ºçĽ®çļĦ
    0.07
    ä½ĨåıĪ
    0.07
    大ä¸ļ
    0.07
    Activations Density 0.756%

    No Known Activations