© 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. 25428
    Prev
    Next
    INDEX
    Explanations

    fish and aquatic species

    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
    å°ĺ
    -0.08
    èļģ
    -0.08
    èĶĹ
    -0.08
    çIJIJ
    -0.07
    æ´Ĵ
    -0.07
     dusty
    -0.07
     Path
    -0.07
    ä¸ļåĬ¡å·¥ä½ľ
    -0.07
    èĬĴ
    -0.07
    èĮ§
    -0.07
    POSITIVE LOGITS
     fish
    0.13
    åŀĤéĴĵ
    0.12
     fisheries
    0.12
     fishes
    0.12
     fishing
    0.12
    鱼类
    0.12
    å°ıé±¼
    0.12
     ÑĢÑĭб
    0.12
    é±¼çļĦ
    0.12
     fishermen
    0.11
    Activations Density 0.183%

    No Known Activations