© 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. 51465
    Prev
    Next
    INDEX
    Explanations

    wonderful lovely

    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
    å±ĬæŶ
    -0.07
    å¼ķäººæ³¨çĽ®
    -0.06
    “We
    -0.06
    åıĹ欢è¿İçļĦ
    -0.06
    ãģĬ使ãģĦ
    -0.06
    vena
    -0.06
    äºĨåķĬ
    -0.06
     invoking
    -0.06
    è¿ĻäºĽäºĭ
    -0.06
    apple
    -0.06
    POSITIVE LOGITS
    ç»ĻæĪijçļĦ
    0.09
    对æĪijæĿ¥è¯´
    0.09
    è®ĵæĪij
    0.08
    æĬĬæĪijçļĦ
    0.08
     meiner
    0.08
    带æĪij
    0.08
    æĬĬæĪij
    0.08
    åѦåĪ°äºĨå¾Īå¤ļ
    0.07
    è©ķåĥ¹
    0.07
    !!!!
    0.07
    Activations Density 0.649%

    No Known Activations