© 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. 21483
    Prev
    Next
    INDEX
    Explanations

    originated / origin

    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
    dep
    -0.07
    å±ĬæŶ
    -0.07
     dÆ°
    -0.07
    heed
    -0.07
    åľ¨åģļ好
    -0.07
    å¹³æŶ
    -0.07
    便è¦ģ
    -0.07
    çľĭ好çļĦ
    -0.07
    åģļ好çļĦ
    -0.07
    emos
    -0.07
    POSITIVE LOGITS
    æľĢæĹ©
    0.18
     originated
    0.18
    èµ·æºIJ
    0.18
    èµ·æºIJäºİ
    0.17
     originally
    0.16
     originate
    0.16
    origin
    0.16
    æľĢæĹ©çļĦ
    0.16
     originates
    0.15
     origin
    0.15
    Activations Density 1.078%

    No Known Activations