© 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. 8939
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with multiplication

    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
    åt
    -0.09
    зÑĮ
    -0.08
    icamente
    -0.08
    ajara
    -0.07
    人åħ³æ³¨
    -0.07
    óf
    -0.07
    åѦçĶŁå®¶éķ¿
    -0.07
    åĴĮåIJĮåѦ
    -0.07
    èģĮä¸ļåѦéĻ¢
    -0.07
    ous
    -0.07
    POSITIVE LOGITS
    áĢ¸
    0.07
    è¥Ħ
    0.06
    çŃĸ
    0.06
    ÙĬاÙĨ
    0.06
    åı¸
    0.06
    çİ¥
    0.06
    lean
    0.06
     chast
    0.06
    leftright
    0.06
    éĢ¢
    0.06
    Activations Density 0.008%

    No Known Activations