© 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. 1349
    Prev
    Next
    INDEX
    Explanations

    bouncycastle, _dec, pregnant, protect, Albania, Faerie, patts, TNBC, bleeding, irritable

    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
    æĺł
    -0.07
    -ts
    -0.07
    elsing
    -0.07
    常
    -0.07
    itele
    -0.06
    æħ¢
    -0.06
     Grie
    -0.06
    jej
    -0.06
    apsed
    -0.06
    jes
    -0.06
    POSITIVE LOGITS
    hani
    0.09
     âĵĺ
    0.08
    pas
    0.08
    azor
    0.08
     Nha
    0.07
    asset
    0.07
    麹
    0.07
    elier
    0.07
    æįIJ
    0.07
    å¾·éĩĮ
    0.07
    Activations Density 0.708%

    No Known Activations