© 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. 65325
    Prev
    Next
    INDEX
    Explanations

    interface description

    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
    anh
    -0.07
    æķĻèĤ²æĺ¯
    -0.07
    飧
    -0.07
    åı
    -0.07
    getSingleton
    -0.07
    çĭ¬ç«ĭ
    -0.06
    å±Ģåľ°
    -0.06
    ilah
    -0.06
    acent
    -0.06
    æĹ¥åħī
    -0.06
    POSITIVE LOGITS
    æł¼å¼ı
    0.09
    udin
    0.08
     format
    0.08
    è¾ĵåĩºçļĦ
    0.07
    onii
    0.07
    _FORMAT
    0.07
     formatted
    0.07
     output
    0.07
    ellig
    0.07
    èª
    0.07
    Activations Density 0.001%

    No Known Activations