© 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. 32668
    Prev
    Next
    INDEX
    Explanations

    modal verbs and likelihood indicators

    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
    ustry
    -0.08
    à¹Īำ
    -0.07
    çĤľ
    -0.07
     arguably
    -0.07
     whenever
    -0.07
    _asset
    -0.07
    åĩłä¹İ
    -0.07
    建éĢłå¸Ī
    -0.07
    alls
    -0.07
    .utcnow
    -0.07
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.10
    unlikely
    0.09
    ä¸įä¼ļæĺ¯
    0.09
    大æ¦Ĥçİĩ
    0.09
    ä¸įä¼ļåĩºçİ°
    0.09
    ä¸įä¼ļæľī
    0.09
     unlikely
    0.09
     irgende
    0.08
     probably
    0.08
    éĥ½ä¸įä¼ļ
    0.08
    Activations Density 0.282%

    No Known Activations