© 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. 14924
    Prev
    Next
    INDEX
    Explanations

    floating point numbers

    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
     ripar
    -0.09
    达产
    -0.08
    lbrace
    -0.08
    enance
    -0.08
     Mua
    -0.08
    -lfs
    -0.08
    à¸ĩาม
    -0.08
    filtro
    -0.08
    åĴĮçī¹çĤ¹
    -0.08
    /remove
    -0.08
    POSITIVE LOGITS
    精度
    0.07
    Convertible
    0.07
    æĵ¦
    0.06
    使çĶ¨èµ·æĿ¥
    0.06
    æī±ãģĦ
    0.06
    ToInt
    0.06
    inkel
    0.06
    -based
    0.06
    æĢĿç»´
    0.06
     accuracy
    0.06
    Activations Density 0.006%

    No Known Activations