© 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. 4300
    Prev
    Next
    INDEX
    Explanations

    It could possibly be

    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
    ınd
    -0.08
    rary
    -0.07
    æį®æѤ
    -0.07
    åħ¼å¹¶
    -0.07
    éĻIJåĪ¶æ¶Īè´¹
    -0.07
    ived
    -0.07
    _FORE
    -0.07
    aspers
    -0.07
    ç´ħèijī
    -0.07
    ä¹ŁæľīäºĽ
    -0.06
    POSITIVE LOGITS
    ä¸įèĥ½è¢«
    0.07
    orem
    0.07
    微信æī«ä¸Ģæī«
    0.07
    åľ¨æľ¬
    0.07
     yourself
    0.07
    ums
    0.06
    olla
    0.06
     Pend
    0.06
    ä¹ĭæīĢ以
    0.06
    irman
    0.06
    Activations Density 0.001%

    No Known Activations