© 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. 3425
    Prev
    Next
    INDEX
    Explanations

    numbers and specific identifiers

    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
    æīĢ以对äºİ
    -0.08
    iens
    -0.07
    tek
    -0.07
    被ä»ĸ
    -0.07
    è¢«ä½ł
    -0.07
    让è¿ĻäºĽ
    -0.07
    ä¼¼ä¹İä¹Ł
    -0.06
    äººä¸ºæľ¬
    -0.06
    моÑĤ
    -0.06
    å°±æĺ¯è¿Ļä¹Ī
    -0.06
    POSITIVE LOGITS
    ãģ¨ãģĦãģĪãģ°
    0.09
    ãģ¨è¨ĢãģĪãģ°
    0.08
    çŁ¥ç½ij
    0.08
    åĪĿå¤ı
    0.07
    åıªæľīåľ¨
    0.07
    主è¦ģçĶ¨äºİ
    0.07
     spetta
    0.07
    å¸Į
    0.07
     inaug
    0.07
    éĽ
    0.07
    Activations Density 0.037%

    No Known Activations