© 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. 63266
    Prev
    Next
    INDEX
    Explanations

    year at, physical, truck, forum, download, expert

    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
    ç«ĭåį³ä¸ĭè½½
    -0.09
    åIJİåį³åı¯
    -0.09
    å·¥åķĨè¡ĮæĶ¿ç®¡çIJĨå±Ģ
    -0.08
    ä½ķçŃī
    -0.08
    秸
    -0.08
    æ·ĺå®Ŀç½ij
    -0.08
    éĿŀ常åĩºèī²
    -0.08
    ieden
    -0.08
    ä¸įå¤ļ说
    -0.08
    çĶµèĦijçīĪ
    -0.08
    POSITIVE LOGITS
    ðŁ
    0.10
    ðŁĺ
    0.10
    .......
    0.09
    Âł
    0.09
    ....
    0.09
    åijĥ
    0.08
    ...
    0.08
    ä»Ģä¹ĪçļĦ
    0.08
    ï¿
    0.08
    .....
    0.08
    Activations Density 0.948%

    No Known Activations