© 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. 48242
    Prev
    Next
    INDEX
    Explanations

    days ago

    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
    pollo
    -0.07
     Auge
    -0.07
    anggil
    -0.06
     ninth
    -0.06
     ÑĢода
    -0.06
     seventh
    -0.06
    ÙĪدÙĩ
    -0.06
    roso
    -0.06
    å±ħ
    -0.06
    .listen
    -0.06
    POSITIVE LOGITS
    æĹ¢çĦ¶
    0.08
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    0.08
    ibar
    0.07
    è¿Ļæĺ¯å¯¹
    0.07
    holm
    0.07
    åIJĮæł·æĺ¯
    0.07
     Raffa
    0.07
    åIJĮæł·çļĦ
    0.07
    LESS
    0.07
    èĢģå¸Īåľ¨
    0.07
    Activations Density 0.105%

    No Known Activations