© 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. 45050
    Prev
    Next
    INDEX
    Explanations

    shows, as, price

    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
    æ§ĺ
    -0.07
    å±±éķĩ
    -0.07
    ä¸įä¼ļåĽłä¸º
    -0.07
     sogenannten
    -0.07
    被å°ģ
    -0.06
    é¦Ĵ
    -0.06
    ono
    -0.06
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    -0.06
    å¸ĮæľĽåı¯ä»¥
    -0.06
    ä¸įèĩªè§ī
    -0.06
    POSITIVE LOGITS
    两å¤Ħ
    0.09
     missing
    0.08
     apparently
    0.08
    arently
    0.08
    äºĮ段
    0.08
     admittedly
    0.07
    missing
    0.07
    rase
    0.07
    éĶ¦æ¶Ľ
    0.07
    两次
    0.07
    Activations Density 0.123%

    No Known Activations