© 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. 9190
    Prev
    Next
    INDEX
    Explanations

    batch 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
    ä¹ĭçªĹ
    -0.07
    aldas
    -0.07
    pag
    -0.07
    occhi
    -0.07
    ä¸ĢåĪĩçļĦ
    -0.07
    TextNode
    -0.07
    ollo
    -0.07
    ÙĪÙĦÙĪج
    -0.07
    åIJĿåķ¬
    -0.06
    å¼ĢèĢĥ
    -0.06
    POSITIVE LOGITS
     halinde
    0.15
    人马
    0.10
     size
    0.10
    çĬ¶
    0.09
     sizes
    0.09
    åŃIJéĩĮ
    0.09
    /group
    0.09
    /groups
    0.09
    次çļĦ
    0.09
     Size
    0.09
    Activations Density 0.227%

    No Known Activations