© 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. 64570
    Prev
    Next
    INDEX
    Explanations

    United States history, professional divers, religion used, social games, human predictions

    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
     videor
    -0.10
    æĭŃ缮
    -0.09
    oleans
    -0.09
    åIJĪä½ľåķĨæľº
    -0.09
    åºĹéĵºç»ıèIJ¥èĢħ
    -0.09
    èµŀåIJĮåħ¶è§ĤçĤ¹
    -0.09
    راÙħ
    -0.09
    licer
    -0.09
    دا
    -0.09
    ijker
    -0.09
    POSITIVE LOGITS
     P
    0.06
    0.06
    J
    0.06
     e
    0.06
    w
    0.06
     (
    0.06
     J
    0.06
    awi
    0.05
     I
    0.05
    ef
    0.05
    Activations Density 0.012%

    No Known Activations