© 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. 32719
    Prev
    Next
    INDEX
    Explanations

    code comments and scripting

    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
    Ĥ
    -0.07
    èĮ¹
    -0.07
    éĩİèĽ®
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
    é¡
    -0.06
    åIJijè®°èĢħ
    -0.06
    caret
    -0.06
    æŀľçľŁ
    -0.06
    Pros
    -0.06
    ="@
    -0.06
    POSITIVE LOGITS
     Uncomment
    0.10
     uncomment
    0.09
     ....
    0.08
    ners
    0.07
    ....
    0.07
    enes
    0.07
    alÄĥ
    0.07
    ä»»éĩį
    0.07
    agram
    0.07
    naud
    0.07
    Activations Density 0.208%

    No Known Activations