© 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. 16203
    Prev
    Next
    INDEX
    Explanations

    bibliographic citation reference

    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
    apot
    -0.07
    ertz
    -0.07
    à¹Ģà¸ģ
    -0.06
    allet
    -0.06
    è¿ĩéģĵ
    -0.06
     impl
    -0.06
     getModel
    -0.06
    æĮĩæĺİäºĨ
    -0.06
     Abed
    -0.06
    ustru
    -0.06
    POSITIVE LOGITS
    uron
    0.07
     CHÃļ
    0.07
    eball
    0.07
    ¡°
    0.07
    åĪ»
    0.07
    人å±ħ
    0.07
    好å¿ĥ
    0.07
    iao
    0.07
    rotch
    0.07
    ä¸īåĮħ
    0.07
    Activations Density 0.003%

    No Known Activations