© 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. 16081
    Prev
    Next
    INDEX
    Explanations

    livestock and crops

    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
    èı
    -0.07
    åİŁä»¶åıĬ
    -0.07
     Summon
    -0.07
    éĢłç¦ı
    -0.07
     medical
    -0.07
    带çĶµ
    -0.07
    ä¼ģä¸ļä¸ļåĬ¡
    -0.06
    åĬŀæ¡Ī
    -0.06
    ikker
    -0.06
     reusable
    -0.06
    POSITIVE LOGITS
    irage
    0.10
    æıIJæĹ©
    0.09
    éĢĤå®ľçļĦ
    0.08
    OPSIS
    0.08
    -season
    0.08
     scrimmage
    0.08
     ÑĤоваÑĢ
    0.08
     ìĤ¬ìĸij
    0.08
    åIJĪçIJĨåĮĸ
    0.08
     infield
    0.08
    Activations Density 0.185%

    No Known Activations