© 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. 27558
    Prev
    Next
    INDEX
    Explanations

    transforming into something else

    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
    vlak
    -0.07
    è¾ľ
    -0.07
    åı£åŃIJ
    -0.07
    ettu
    -0.07
    iggins
    -0.07
    inna
    -0.06
    æī¯
    -0.06
     Viel
    -0.06
    uket
    -0.06
    èµĤ
    -0.06
    POSITIVE LOGITS
    转åĮĸçļĦ
    0.12
    转åĮĸæĪIJ
    0.12
    转åĮĸ
    0.12
    à¹ģà¸Ľà¸¥à¸ĩ
    0.11
    åıĺæĪIJ
    0.11
     into
    0.11
    转åıĺ为
    0.11
    ä¸Ģåıĺ
    0.11
     تبدÛĮÙĦ
    0.10
     transform
    0.10
    Activations Density 0.136%

    No Known Activations