© 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. 17150
    Prev
    Next
    INDEX
    Explanations

    examples and notable instances

    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
    æľĢæĢķ
    -0.08
    ostar
    -0.07
    olim
    -0.07
    è®¤è®¤çľŁ
    -0.07
    åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    Islam
    -0.07
    chau
    -0.07
     selfies
    -0.06
     Unauthorized
    -0.06
     adul
    -0.06
    POSITIVE LOGITS
    èijĹåIJįçļĦ
    0.09
    诸å¦Ĥ
    0.09
     notable
    0.08
     például
    0.08
     napÅĻÃŃklad
    0.08
     notably
    0.08
     esimerkiksi
    0.08
     famous
    0.08
    çļĦä¸ĢäºĽ
    0.08
    享èªī
    0.07
    Activations Density 0.152%

    No Known Activations