© 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. 57562
    Prev
    Next
    INDEX
    Explanations

    lists of topics or subjects

    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
    bis
    -0.08
    á»
    -0.07
    paren
    -0.07
    æĬĢæľ¯éĹ®é¢ĺ
    -0.07
    æĮĩ示
    -0.07
    amba
    -0.06
    aldo
    -0.06
    chw
    -0.06
    enne
    -0.06
    åij¼åºĶ
    -0.06
    POSITIVE LOGITS
    主è¦ģåĮħæĭ¬
    0.12
    诸å¦Ĥ
    0.10
    åĩ¡æĺ¯
    0.09
    ä¸įåĮħæĭ¬
    0.09
    è¿ĺåĮħæĭ¬
    0.08
    åºĶåĮħæĭ¬
    0.08
    itelist
    0.08
    åĵªäºĽ
    0.08
    æľīåĵªäºĽ
    0.08
    缴æİ¥æĪĸéĹ´æİ¥
    0.08
    Activations Density 0.008%

    No Known Activations