© 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. 22170
    Prev
    Next
    INDEX
    Explanations

    purple, butter, woman, carrot

    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
    onsel
    -0.07
    )))),
    -0.07
    ãģĵãģĨãģĹãģŁ
    -0.07
    ä¾¥
    -0.06
    apan
    -0.06
    åĺĽ
    -0.06
    è¿Ļç±»
    -0.06
    ³³
    -0.06
    该车
    -0.06
     ,
    -0.06
    POSITIVE LOGITS
    éĤ£ä¸¤ä¸ª
    0.09
    cco
    0.08
    çĽİ
    0.08
    attan
    0.08
    æīĢ示
    0.08
     mentioned
    0.08
    ç½ĹéĤ£
    0.08
    éĤ£åı¥è¯Ŀ
    0.07
     kia
    0.07
    Ñĥда
    0.07
    Activations Density 0.258%

    No Known Activations