© 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. 12404
    Prev
    Next
    INDEX
    Explanations

    CSS `tag` and `color`, `payment`

    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
    lus
    -0.08
    ÏĥÏĦι
    -0.08
    æĺĶ
    -0.08
    cardo
    -0.07
    æīİå®ŀåģļ好
    -0.07
    leh
    -0.07
    åįĹåĽ½
    -0.07
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    -0.07
    esas
    -0.07
    OLER
    -0.07
    POSITIVE LOGITS
    åĴĮå¹³
    0.08
     ones
    0.07
    ryn
    0.07
     Grove
    0.06
    enal
    0.06
    åľ¨æī§è¡Į
    0.06
     conveniently
    0.06
    æŁĵ
    0.06
    ç¾ģ
    0.06
    è¦Ĩ
    0.06
    Activations Density 0.068%

    No Known Activations