© 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. 2819
    Prev
    Next
    INDEX
    Explanations

    film setting and plot

    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
    éħįåģ¶
    -0.08
    inal
    -0.07
    ä¸įåĢ¦
    -0.07
    éĢıæĺİ
    -0.07
    italia
    -0.07
     haste
    -0.06
    åĽ¾çīĩæĪĸ
    -0.06
    usch
    -0.06
    çĶ¨äºİ
    -0.06
    tweet
    -0.06
    POSITIVE LOGITS
     fict
    0.09
     fictional
    0.09
     themes
    0.09
    é¡ĮæĿIJ
    0.09
    å¹´æŶéĹ´
    0.09
    讲述äºĨ
    0.08
    设å®ļ
    0.08
    ç´§ç´§åĽ´ç»ķ
    0.08
     explores
    0.08
     realistically
    0.08
    Activations Density 0.444%

    No Known Activations