© 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. 61703
    Prev
    Next
    INDEX
    Explanations

    words like "us" and "facts"

    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
     ë¿IJë§Į
    -0.08
    ä¸įä»ħåľ¨
    -0.08
    rous
    -0.07
    ä¸įä»ħè¦ģ
    -0.07
    è¿ĺæľī许å¤ļ
    -0.07
    è¿ĺæľīå¾Īå¤ļ
    -0.07
    åIJĮæŶè¿ĺ
    -0.07
    itung
    -0.07
    ä¸įä»ħèĥ½
    -0.07
    keyp
    -0.07
    POSITIVE LOGITS
     indirectly
    0.12
    åĢĴæĺ¯
    0.12
    åģ¶å°Ķ
    0.12
    个åĪ«
    0.12
    éĹ´æİ¥
    0.12
    æŁIJäºĽ
    0.11
    åľ¨æŁIJäºĽ
    0.11
    åĭī强
    0.10
     occasional
    0.10
     indire
    0.10
    Activations Density 0.068%

    No Known Activations