© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    receiving and sending data

    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
    交代
    -0.08
    roje
    -0.07
    éģĹçķĻ
    -0.07
    æĿ¥æºIJ
    -0.07
    è¡
    -0.07
    ovre
    -0.07
    ä¾ĨæºIJ
    -0.07
    åĴĮ游æĪı
    -0.07
    ellan
    -0.06
    ibro
    -0.06
    POSITIVE LOGITS
    æİ¥æĶ¶
    0.21
     receiving
    0.17
    æİ¥åıĹ
    0.17
     receptive
    0.17
     recept
    0.16
    æİ¥åıĹçļĦ
    0.16
     receptors
    0.15
     receptor
    0.15
     receiver
    0.15
     receptions
    0.15
    Activations Density 0.633%

    No Known Activations