© 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. 12886
    Prev
    Next
    INDEX
    Explanations

    imperative verb start

    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
    çİ°åľ¨è¿ĺ
    -0.07
    ernes
    -0.07
    lah
    -0.07
    ange
    -0.07
    ķ
    -0.07
    åĪ°çİ°åľ¨
    -0.07
    ena
    -0.06
    é¸Ń
    -0.06
    _SEQUENCE
    -0.06
     Oct
    -0.06
    POSITIVE LOGITS
    ihu
    0.08
    ropri
    0.08
    ignum
    0.08
    :[[
    0.08
    æĭ
    0.08
    رÙĪÙĬ
    0.08
     Suff
    0.08
    åIJĦçıŃ
    0.07
    못
    0.07
    å¼ĺ
    0.07
    Activations Density 0.001%

    No Known Activations