© 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. 40245
    Prev
    Next
    INDEX
    Explanations

    just followed by past participle

    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
     eventually
    -0.08
     eventual
    -0.08
    以åIJİåĨį
    -0.08
    धà¥Ģ
    -0.08
    èĥ¡æĢĿ
    -0.08
    itik
    -0.07
     ultimately
    -0.07
     Eventually
    -0.07
    åħĪ导
    -0.07
    æľĢç»ĪçļĦ
    -0.07
    POSITIVE LOGITS
    ä¸įä¹ħçļĦ
    0.13
    ä¸įä¹ħ
    0.11
    ãģ°ãģĭãĤĬ
    0.10
    没å¤ļä¹ħ
    0.10
     недавно
    0.09
    åĩºçĤī
    0.09
    åĪļåĪļ
    0.09
     mẻ
    0.08
    ä¹ĭéĻħ
    0.08
    ä¸įä¹ħåīį
    0.08
    Activations Density 0.146%

    No Known Activations