© 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. 8795
    Prev
    Next
    INDEX
    Explanations

    etc

    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
    chiere
    -0.10
    åīįæĸ¹çļĦ
    -0.07
    ioso
    -0.07
     DEV
    -0.07
    ekut
    -0.07
    ä¸įèIJ½
    -0.07
    奸
    -0.07
    æĬĵä½ıäºĨ
    -0.07
    èݱ德
    -0.06
    "."
    -0.06
    POSITIVE LOGITS
     etc
    0.11
    etc
    0.08
    çŃīçŃī
    0.08
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.08
    å¢ŀåĩı
    0.08
    ç§įç§įåİŁåĽł
    0.08
    çŃīå¤Ħ
    0.07
    æľĢéĩįè¦ģçļĦæĺ¯
    0.07
    åĬ¨æ¤įçī©
    0.07
    èĹ
    0.07
    Activations Density 0.199%

    No Known Activations