© 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. 58664
    Prev
    Next
    INDEX
    Explanations

    referred to as

    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
    æĪIJç«ł
    -0.07
    å±ķå¼Ģåħ¨æĸĩ
    -0.07
    Ã¶ÃŁ
    -0.06
    IGH
    -0.06
    åħ®
    -0.06
    }}</
    -0.06
    orios
    -0.06
    ORN
    -0.06
    )`
    -0.06
    ë¹ĦìķĦ
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºæĪij
    0.08
    nade
    0.07
    åĽłä¸ºæĪij们
    0.07
    æĬķèµĦæĪĸ
    0.07
    ()',
    0.07
    æĢ§æĪĸ
    0.07
     ÙĦØ£ÙĨÙĩا
    0.07
    aley
    0.07
    åĽłä¸ºå®ĥ们
    0.07
    urement
    0.07
    Activations Density 0.366%

    No Known Activations