© 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. 8927
    Prev
    Next
    INDEX
    Explanations

    chewy, secretory, detangled

    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
    etration
    -0.07
    æľ¬èº«
    -0.07
    ardon
    -0.07
    ↵      ↵
    -0.07
    æľ¬èº«çļĦ
    -0.07
    ÑģкиÑı
    -0.07
    å®ŀä½ĵ
    -0.07
    æīĭå¿Ļ
    -0.07
    è¿ħ鼷
    -0.07
    并åIJĮæŶ
    -0.06
    POSITIVE LOGITS
    able
    0.07
    åĬĽå¼º
    0.07
    nz
    0.07
    ables
    0.07
    ugg
    0.07
    çļĦéĤ£ç§į
    0.07
    ä¸įæĿ¥
    0.06
    Ùģت
    0.06
    è¯ı
    0.06
    lee
    0.06
    Activations Density 0.317%

    No Known Activations