© 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. 12692
    Prev
    Next
    INDEX
    Explanations

    hybrid vehicle, AT, DCT, AR technology, circulating fluidized bed reactor, fluid column

    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
    igg
    -0.08
    rew
    -0.07
    æĸ¹åIJijåĴĮ
    -0.07
    好好çļĦ
    -0.07
    åĩ«
    -0.07
    å¦Ĥæŀľä»ĸ们
    -0.06
    æĻ®æŁ¥
    -0.06
    iedi
    -0.06
     gh
    -0.06
    ippi
    -0.06
    POSITIVE LOGITS
     consiste
    0.08
    amakan
    0.08
     polega
    0.08
    ç²¾é«ĵ
    0.08
     consists
    0.08
     Variante
    0.08
    强è°ĥçļĦæĺ¯
    0.07
     ÑģÑĥÑĤÑĮ
    0.07
    .wikipedia
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    Activations Density 0.042%

    No Known Activations