© 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. 20112
    Prev
    Next
    INDEX
    Explanations

    pests and insects

    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
    åĮ»çĸĹäºĭæķħ
    -0.07
    æ·¤
    -0.07
    åºŁ
    -0.06
     healing
    -0.06
    修饰
    -0.06
    溺水
    -0.06
     shape
    -0.06
    å¼¥
    -0.06
    æĹłåģ¿çĮ®è¡Ģ
    -0.06
     explored
    -0.06
    POSITIVE LOGITS
     pests
    0.11
    åĩºæ²¡
    0.10
     pest
    0.10
    ç¹ģæ®ĸ
    0.09
    害èĻ«
    0.09
     insects
    0.09
     наÑģеком
    0.09
     larvae
    0.09
     insect
    0.09
     ÑĢазмно
    0.09
    Activations Density 0.168%

    No Known Activations