© 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. 7822
    Prev
    Next
    INDEX
    Explanations

    true or false questions

    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
    ONO
    -0.09
    agni
    -0.08
    ÑĢай
    -0.08
    ļĮ
    -0.08
    ãĥĥãĤ³
    -0.08
    amenta
    -0.08
    HeaderValue
    -0.08
    <article
    -0.08
    åħ·é«Ķ
    -0.08
    urgi
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įä¸Ģå®ļ
    0.09
    ä¸įä¸Ģå®ļ
    0.08
    ä¸įä¸Ģå®ļæĺ¯
    0.07
    èĥ½ä¿Ŀè¯ģ
    0.07
    åħ³ç³»
    0.07
    ä½łæ°¸è¿ľ
    0.07
    çŁ¥
    0.07
    身
    0.07
    çĮľæĥ³
    0.07
     intuit
    0.07
    Activations Density 0.084%

    No Known Activations