© 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. 32804
    Prev
    Next
    INDEX
    Explanations

    questions ending in punctuation

    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
    æĸ°æŃĮ
    -0.09
    ož
    -0.09
    apun
    -0.09
    alat
    -0.08
     insomma
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    æĭ³éģĵ
    -0.08
    ieux
    -0.08
    iagnostics
    -0.08
    bolo
    -0.08
    POSITIVE LOGITS
    0.07
     -
    0.07
    ↵
    0.07
    :
    0.06
     '
    0.06
     [
    0.06
     &
    0.06
    :a
    0.06
    ,
    0.05
    .
    0.05
    Activations Density 0.253%

    No Known Activations