© 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. 25212
    Prev
    Next
    INDEX
    Explanations

    developer console and website admin

    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
    çĶµé¥Ń
    -0.07
    ç«¿
    -0.06
     exert
    -0.06
    æĬĺåIJĪ
    -0.06
    åı¯æľĽ
    -0.06
    宵
    -0.06
    ç²¾æīĵ
    -0.06
    çĶļ
    -0.06
    主ä½ĵç»ĵæŀĦ
    -0.06
    èĥ½éĢĤåºĶ
    -0.06
    POSITIVE LOGITS
    ä»»ä¸Ģ
    0.11
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.08
    æĪĸéĢļè¿ĩ
    0.08
    your
    0.08
    è§Ĥ
    0.08
    ç®Ģæĺĵ
    0.08
    ä»»ä½ķä¸Ģ个
    0.08
    /*/
    0.08
    天èµIJ
    0.07
    å·¥ä½ľæĪĸ
    0.07
    Activations Density 0.348%

    No Known Activations