© 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. 17542
    Prev
    Next
    INDEX
    Explanations

    years since they were sent

    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
    itin
    -0.07
    imo
    -0.07
    ingo
    -0.07
    å½Į
    -0.07
    Äĩi
    -0.07
    enko
    -0.07
    yang
    -0.07
    ÑĽÐ¸
    -0.06
    åĮ»ç§ij大åѦ
    -0.06
     poda
    -0.06
    POSITIVE LOGITS
    缸éĢ¢
    0.07
    มาà¸Ļ
    0.07
     beg
    0.07
    sgiving
    0.06
    èĢĮ对äºİ
    0.06
    åĨįèĢħ
    0.06
    TargetException
    0.06
    ê¹
    0.06
    æĢ»å±Ģ
    0.06
    ermal
    0.06
    Activations Density 0.161%

    No Known Activations