© 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. 45086
    Prev
    Next
    INDEX
    Explanations

    pollination and bees

    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
    ç¾Ķ
    -0.08
    ìĤ¬íķŃ
    -0.07
    çĽĺæķ´
    -0.07
     flex
    -0.07
     Crystal
    -0.07
    æī¿åıĹèĥ½åĬĽ
    -0.07
    æĶ¶å®¹
    -0.07
    é±¼èĤī
    -0.07
    elf
    -0.07
    flex
    -0.07
    POSITIVE LOGITS
    æİĪ
    0.11
    åıĹç²¾
    0.10
    nect
    0.09
     thụ
    0.09
    åĹ¡åĹ¡
    0.09
     insects
    0.09
    ä¸įåŃķ
    0.09
     pollen
    0.08
     poll
    0.08
    æĺĨèĻ«
    0.08
    Activations Density 0.028%

    No Known Activations