© 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. 14110
    Prev
    Next
    INDEX
    Explanations

    recent past time periods

    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
     eventual
    -0.11
     someday
    -0.10
     eventually
    -0.10
    å½ĵå¹´
    -0.10
    æľĢåĪĿ
    -0.10
    åIJİæĿ¥çļĦ
    -0.10
    å½ĵåĪĿ
    -0.10
    later
    -0.10
     later
    -0.09
    æĹ¥åIJİ
    -0.09
    POSITIVE LOGITS
     recently
    0.11
     недавно
    0.10
     recent
    0.10
    åĪļåĪļ
    0.09
     lately
    0.09
    ãģ°ãģĭãĤĬ
    0.09
     اخÛĮر
    0.09
    æľĢè¿ijåľ¨
    0.09
    æľĢè¿ijçļĦ
    0.09
    recent
    0.09
    Activations Density 1.093%

    No Known Activations