© 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. 30761
    Prev
    Next
    INDEX
    Explanations

    POXY

    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
    ISMO
    -0.08
     torrent
    -0.08
    ANDA
    -0.08
    alami
    -0.08
    enza
    -0.07
    amed
    -0.07
    ajang
    -0.07
    igator
    -0.07
    adore
    -0.07
    GetData
    -0.07
    POSITIVE LOGITS
    áºŃc
    0.07
    æĿ¨æŁ³
    0.06
    åŁºäºİ
    0.06
    åıĸåĨ³äºİ
    0.06
    两å¥Ĺ
    0.06
    度
    0.06
    è°·
    0.06
     depending
    0.06
     Goldberg
    0.06
     indexing
    0.06
    Activations Density 0.001%

    No Known Activations