© 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. 14396
    Prev
    Next
    INDEX
    Explanations

    types of

    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
    ç½
    -0.07
    åıijçĶŁåľ¨
    -0.07
    è¾
    -0.06
    bert
    -0.06
    çĮ
    -0.06
    åĩĽ
    -0.06
    顺
    -0.06
    æ±½è½¦éĽ¶éĥ¨ä»¶
    -0.06
    æģŃ
    -0.06
    å«
    -0.06
    POSITIVE LOGITS
    åŀĭå¼ı
    0.11
    åľ¨å¸Ĥåľºä¸Ĭ
    0.11
    รุà¹Īà¸Ļ
    0.10
    å¸ĤéĿ¢ä¸Ĭ
    0.10
    åŀĭåı·
    0.10
    æĸ°åŀĭçļĦ
    0.10
    使çĶ¨å¹´éĻIJ
    0.09
     marketed
    0.09
     designs
    0.09
     ÑĤипÑĥ
    0.09
    Activations Density 0.817%

    No Known Activations