© 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. 35060
    Prev
    Next
    INDEX
    Explanations

    question marks and categories

    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
    IPS
    -0.07
    ä¸ľè¥¿
    -0.07
    ipro
    -0.07
     toilette
    -0.07
    UTIL
    -0.07
    ötz
    -0.07
    æŁļ
    -0.07
    تÙĥ
    -0.07
    åĴĮ缮æłĩ
    -0.07
    =target
    -0.07
    POSITIVE LOGITS
     Category
    0.07
    -category
    0.07
    Category
    0.07
    _CATEGORY
    0.07
     depending
    0.07
     category
    0.07
    /category
    0.07
    姬
    0.07
    /rfc
    0.06
    é¢ĩ
    0.06
    Activations Density 0.005%

    No Known Activations