© 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. 28247
    Prev
    Next
    INDEX
    Explanations

    question words and auxiliary verbs

    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
    ÑĢаÑĤи
    -0.07
    alled
    -0.07
     somehow
    -0.07
     “
    -0.07
    ä¸įéĹ®
    -0.07
    ä½ķ为
    -0.06
    angk
    -0.06
    ansi
    -0.06
    âĢij
    -0.06
     briefed
    -0.06
    POSITIVE LOGITS
     Ùħزد
    0.08
    å¦ĸ
    0.07
    ...",
    0.07
    distinct
    0.07
    æĽ³
    0.07
    æļĤ
    0.07
    va
    0.07
    aea
    0.07
    çłĶ究人åijĺ
    0.07
    ATEST
    0.07
    Activations Density 0.009%

    No Known Activations