© 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. 46818
    Prev
    Next
    INDEX
    Explanations

    code rules and names

    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
    ات
    -0.12
    es
    -0.08
    s
    -0.08
    ×Ļ×Ŀ
    -0.08
    sie
    -0.08
    ãģĦãĤĭ
    -0.08
    arli
    -0.08
    itter
    -0.07
    sstr
    -0.07
    Ñĭ
    -0.07
    POSITIVE LOGITS
    o
    0.10
    a
    0.09
    ly
    0.09
    ror
    0.08
    rar
    0.08
    oar
    0.08
    ر
    0.08
    à§įড
    0.07
    rf
    0.07
    ا
    0.07
    Activations Density 0.001%

    No Known Activations