© 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. 18556
    Prev
    Next
    INDEX
    Explanations

    two methods, formats, or types

    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
    inary
    -0.07
    Ù°
    -0.07
     سر
    -0.07
     spatial
    -0.06
     ìłģ
    -0.06
    ä¸Ģé¢Ĺ
    -0.06
    åĬłåĩı
    -0.06
    onga
    -0.06
    éĢĨ
    -0.06
    seudo
    -0.06
    POSITIVE LOGITS
    两ç§įæĸ¹å¼ı
    0.19
    两ç§į
    0.17
    è¿Ļ两ç§į
    0.16
    å¤ļç§įæĸ¹å¼ı
    0.14
    åħ©ç¨®
    0.14
    çŃīå¤ļç§į
    0.13
    å¤ļç§į
    0.13
    ä¸īç§į
    0.13
    第ä¸Ģç§į
    0.12
    æľīå¤ļç§į
    0.12
    Activations Density 0.194%

    No Known Activations