© 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. 38691
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and modifiers

    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
     «
    -0.09
    %;">
    -0.08
    bart
    -0.08
    )","
    -0.08
    iog
    -0.08
    )">
    -0.07
    ä¿Ĺè¯Ŀ说
    -0.07
    >}
    -0.07
    anson
    -0.07
    ">\
    -0.07
    POSITIVE LOGITS
    0.10
    ly
    0.09
    atre
    0.08
    çī¹å°Ķ
    0.08
     (!
    0.08
    æĸ°åĬłåĿ¡
    0.07
    HING
    0.07
     (?)
    0.07
    ostante
    0.07
    (tm
    0.07
    Activations Density 0.062%

    No Known Activations