© 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. 34468
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    ä¸Ģè§Ī
    -0.08
     abon
    -0.07
    èµĦæĸĻä¸ĭè½½
    -0.07
    ä¸¤çľ¼
    -0.07
    chooser
    -0.07
    ieti
    -0.07
    Reviewer
    -0.07
    çŃĨèĢħ
    -0.07
    à¸ŀà¸ĩ
    -0.07
    .Dynamic
    -0.07
    POSITIVE LOGITS
    询éĹ®
    0.11
     asking
    0.09
     asks
    0.09
    å°±éĹ®
    0.09
    éĹ®
    0.09
     interloc
    0.08
    éĹ®åıĬ
    0.08
    对è¯Ŀ
    0.08
    質åķı
    0.08
     asked
    0.08
    Activations Density 0.192%

    No Known Activations