© 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. 11370
    Prev
    Next
    INDEX
    Explanations

    have + past participle or infinitive

    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
     themselves
    -0.13
    æ¯ĶæĪij们
    -0.10
    æĪij们çľĭåĪ°
    -0.10
     ours
    -0.09
    èĢĮæĪij们
    -0.09
     quedarse
    -0.09
    æĪij们认为
    -0.09
    æĪij们åıijçİ°
    -0.09
    æĪij们å¸ĮæľĽ
    -0.09
     нами
    -0.09
    POSITIVE LOGITS
     myself
    0.24
    æĪijèĩªå·±çļĦ
    0.17
    æĪijèĩªå·±
    0.15
    让æĪijçļĦ
    0.14
    æĬĬæĪijçļĦ
    0.13
     personally
    0.13
    åĴĮæĪijçļĦ
    0.13
     ÙĨÙģسÙĬ
    0.12
    åĽłä¸ºæĪij
    0.11
    æĺ¯ä¸ĢåIJį
    0.11
    Activations Density 3.873%

    No Known Activations