© 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. 10832
    Prev
    Next
    INDEX
    Explanations

    blood function, ability, parameters, facilitate, contain, increasing

    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
    æĻĮ
    -0.08
    è¦ģæ±Ĥè¿Ľè¡Į
    -0.07
    éľ²
    -0.07
    ölker
    -0.07
    æŶæľīåıijçĶŁ
    -0.07
    AtA
    -0.07
    å¾ĪæĹ©
    -0.06
     поздно
    -0.06
    çļĦä¸ĢäºĽ
    -0.06
    æľīä¸įåIJĮçļĦ
    -0.06
    POSITIVE LOGITS
    æĶ¹åĸĦ
    0.09
    restore
    0.08
    è§ģæķĪ
    0.08
    ä»İæł¹æľ¬ä¸Ĭ
    0.08
     restores
    0.08
    æľ¬èģĮå·¥ä½ľ
    0.08
    åħħçĽĪ
    0.08
    cott
    0.08
    åIJĮæŶå°Ĩ
    0.08
    容积
    0.08
    Activations Density 0.002%

    No Known Activations