© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30458
    Prev
    Next
    INDEX
    Explanations

    InlineData((TypeLibVarFlags)(-1))

    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
    isan
    -0.08
    strup
    -0.07
    imon
    -0.07
    ÙģتÙĩ
    -0.07
    ever
    -0.07
    人å¿ĥ弦
    -0.06
    ajor
    -0.06
    æĸ¹æĸ¹éĿ¢
    -0.06
    æĸ¹å¼ı使çĶ¨
    -0.06
    OrFail
    -0.06
    POSITIVE LOGITS
    ãģªãģĹ
    0.09
    ispo
    0.08
    uwe
    0.07
    acap
    0.07
    çĦ¡ãģĹ
    0.07
    zio
    0.07
    adah
    0.07
    为ä»Ģä¹Īä¸į
    0.07
     Himself
    0.07
    -po
    0.07
    Activations Density 0.027%

    No Known Activations