© 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. 56504
    Prev
    Next
    INDEX
    Explanations

    talk show host, iPhone, iPad, OSN, screenwriters, blues musician, titleholder

    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
    æľĭåıĭçļĦ
    -0.11
    å°ıåŃ©çļĦ
    -0.09
    çĪ¶äº²çļĦ
    -0.08
    æ¯į亲çļĦ
    -0.08
    å¦Īå¦ĪçļĦ
    -0.08
    åIJĮåѦçļĦ
    -0.08
    ä¸Ģ个人çļĦ
    -0.08
    èĢģå¸ĪçļĦ
    -0.08
    们çļĦ
    -0.08
    çĪ¶æ¯įçļĦ
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢåIJį
    0.09
    éķ¿å¤§çļĦ
    0.09
    çļĦä¸Ģåijĺ
    0.09
    áĢŀáĢ°
    0.08
    èİ·å¾ĹèĢħ
    0.08
    主ä¹īèĢħ
    0.08
     wearer
    0.08
    ä¹ĭ士
    0.08
     minded
    0.08
    -using
    0.08
    Activations Density 1.167%

    No Known Activations