© 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. 47059
    Prev
    Next
    INDEX
    Explanations

    cell formation and growth

    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
    æĶ¹åıĺçļĦ
    -0.08
    åı¯æĮģç»Ńåıijå±ķçļĦ
    -0.08
    è¯Ħä»·æĮĩæłĩ
    -0.08
    urge
    -0.07
    ваÑĩ
    -0.07
    æĹ¥ä¸º
    -0.07
    amani
    -0.07
    å¸Ĥåľºçݯå¢ĥ
    -0.07
     assum
    -0.07
    è¯Ħä»·ä½ĵç³»
    -0.07
    POSITIVE LOGITS
    ãģ¸ãģ®
    0.10
    æľĢ大éĻIJ度çļĦ
    0.08
    å°ı说éĺħ读
    0.08
    çŁ¥è¯ĨçļĦ
    0.08
    mentation
    0.08
    å·¥ä½ľçļĦå¼Ģå±ķ
    0.08
     removal
    0.08
    arnation
    0.07
    çļĦå¿«éĢŁ
    0.07
    åĮĸåĴĮ
    0.07
    Activations Density 0.937%

    No Known Activations