© 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. 45761
    Prev
    Next
    INDEX
    Explanations

    demonstrating calculation or proof

    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
     glede
    -0.08
    abut
    -0.08
    кÑĢо
    -0.08
    ัà¸į
    -0.07
    æĹĹä¸ĭ
    -0.07
     datum
    -0.07
    лÑĥм
    -0.07
    ÑĢÑĥм
    -0.07
     Datum
    -0.07
    NavigationView
    -0.07
    POSITIVE LOGITS
    usher
    0.08
    åIJİç»Ń
    0.08
    åIJİç»ŃçļĦ
    0.08
    ä¸ºè¿Ľä¸ĢæŃ¥
    0.07
     later
    0.07
    çĶ¨æĿ¥
    0.07
    æŃ£åľ¨
    0.07
    æŃ£è¦ģ
    0.07
    è¯ķåĽ¾
    0.06
     nantinya
    0.06
    Activations Density 0.271%

    No Known Activations