© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55053
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
    Negative Logits
    èĢĮå½ĵ
    -0.07
    phu
    -0.07
    èĢĮæĹłæ³ķ
    -0.07
     Furthermore
    -0.07
    ipper
    -0.07
    åıĪæĪĸèĢħ
    -0.07
    并ä¸Ķåľ¨
    -0.07
    apte
    -0.06
    究竣æĺ¯ä»Ģä¹Ī
    -0.06
     Moreover
    -0.06
    POSITIVE LOGITS
    rina
    0.08
    esco
    0.08
    ãĥ¼ãĤº
    0.08
    ript
    0.07
    液æĻ¶å±ı
    0.07
    emaker
    0.07
    å°Ķæĸ¯
    0.07
    ếm
    0.07
    oklyn
    0.07
    ediat
    0.07
    Activations Density 0.007%

    No Known Activations