© 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. 13642
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
    ::$
    -0.08
    onn
    -0.07
    ä¸Ń被
    -0.07
    模å¼ıä¸ĭ
    -0.07
    uttur
    -0.07
    isserie
    -0.07
    è·¯éĢı
    -0.07
    ãģĶ確èªįãģıãģłãģķãģĦ
    -0.07
    upy
    -0.07
    åݻ认è¯ģ
    -0.07
    POSITIVE LOGITS
    etch
    0.07
    ä¸İä¹ĭ
    0.07
    odont
    0.07
    essim
    0.07
    åĮĹæµ·
    0.06
     thiêng
    0.06
    usin
    0.06
    hofer
    0.06
    bem
    0.06
    à¹ģร
    0.06
    Activations Density 0.004%

    No Known Activations