© 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. 51022
    Prev
    Next
    INDEX
    Explanations

    modal verbs and questions

    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
    atical
    -0.08
     obed
    -0.08
    æĤ£
    -0.07
    antul
    -0.07
    Õ¡Õ½
    -0.07
     obey
    -0.07
    heim
    -0.07
    uart
    -0.07
    çģ«çĥŃ
    -0.06
    اتÙĩ
    -0.06
    POSITIVE LOGITS
    çĻ½çŁ³
    0.08
    ä¹ĭ以
    0.08
    iz
    0.07
    çļĦåĽŀçŃĶ
    0.07
    WR
    0.07
    åĽŀçŃĶ
    0.07
    ä¸įä»ħè¦ģ
    0.07
    //:
    0.07
    帮åĬ©ä»ĸ们
    0.07
    æİ¥çıŃ人
    0.07
    Activations Density 0.007%

    No Known Activations