© 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. 58475
    Prev
    Next
    INDEX
    Explanations

    specific English words

    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
    +xml
    -0.08
    .Fail
    -0.08
    Chooser
    -0.08
    áĥĽáĥĿ
    -0.08
    anggaran
    -0.08
    osan
    -0.08
    iett
    -0.07
    avigator
    -0.07
    dade
    -0.07
    waan
    -0.07
    POSITIVE LOGITS
    ä¹Łæĺ¯ä¸ºäºĨ
    0.07
    ussin
    0.07
     further
    0.07
    ould
    0.06
     it
    0.06
     then
    0.06
    UBL
    0.06
    fia
    0.06
    æĪIJ大
    0.06
    ãĤĴãģĶ覧ãģıãģłãģķãģĦ
    0.06
    Activations Density 1.268%

    No Known Activations