© 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. 22802
    Prev
    Next
    INDEX
    Explanations

    await followed by async operations

    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
    ếch
    -0.08
     valign
    -0.07
    è¦ģç´§
    -0.07
    zzi
    -0.07
    ç½IJ头
    -0.07
    伤çļĦ
    -0.07
    zio
    -0.07
    =*/
    -0.07
    ivy
    -0.07
    oding
    -0.07
    POSITIVE LOGITS
    edList
    0.08
    edException
    0.08
    ĺ
    0.07
    æĻ´
    0.07
    utenberg
    0.07
    lagen
    0.07
    edImage
    0.07
    åħ¨ç½ij
    0.07
    olfo
    0.06
    çŁ
    0.06
    Activations Density 0.021%

    No Known Activations