© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64017
    Prev
    Next
    INDEX
    Explanations

    all X on Y

    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
    éĵģé¾Ļ
    -0.08
    ç¼Ń
    -0.08
    agod
    -0.08
    :{}
    -0.08
    май
    -0.08
    egger
    -0.08
    bat
    -0.08
    utore
    -0.07
    баÑĤÑĭ
    -0.07
    个åĽŀçŃĶ
    -0.07
    POSITIVE LOGITS
    èĩ³äºİ
    0.08
    ä¸ĢæĹģçļĦ
    0.07
     ÙģÙĩÙĪ
    0.07
     Svens
    0.07
    åĨįåĬłä¸Ĭ
    0.06
    åĪĻæĺ¯
    0.06
     refers
    0.06
    ç»ĵæŀľè¡¨æĺİ
    0.06
    åıĪæĺ¯
    0.06
    æĹ¢çĦ¶æĺ¯
    0.06
    Activations Density 0.016%

    No Known Activations