© 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. 8590
    Prev
    Next
    INDEX
    Explanations

    mathematical or code punctuation

    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
    vak
    -0.08
    æĺ¯ä»Ģä¹Īæł·çļĦ
    -0.07
    odar
    -0.07
    pedia
    -0.07
    æľ¬çĿĢ
    -0.06
    amac
    -0.06
    äºĭ
    -0.06
    åľ¨çº¿éĺħ读
    -0.06
    èĨł
    -0.06
    aturi
    -0.06
    POSITIVE LOGITS
    æ¯ıæĹ¥ä¸Ģç»ĥ
    0.08
    leve
    0.07
    rière
    0.07
    uce
    0.07
    ros
    0.06
    åıĪå¿«
    0.06
    ÏĩÏħ
    0.06
     nhặt
    0.06
     {})
    0.06
    rint
    0.06
    Activations Density 0.104%

    No Known Activations