© 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. 17652
    Prev
    Next
    INDEX
    Explanations

    mainly followed by a verb

    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
    缸è¾ħ缸æĪIJ
    -0.12
    ä¸įåı¯æĢĿè®®
    -0.11
    nell
    -0.10
    arts
    -0.10
    pedia
    -0.10
    ä¼ĹæīĢåij¨çŁ¥
    -0.10
    ãĥ«ãĥķ
    -0.10
    身临åħ¶å¢ĥ
    -0.10
    aison
    -0.09
    dien
    -0.09
    POSITIVE LOGITS
    åĴĮæľĢ
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.08
    ÙĬÙĨ
    0.08
    *
    0.07
    人
    0.07
    Į
    0.07
    "
    0.07
    ä¾ĿéĿł
    0.07
    ç»Ŀ伦
    0.06
    ä¼ĺçĤ¹æĺ¯
    0.06
    Activations Density 0.027%

    No Known Activations