© 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. 33690
    Prev
    Next
    INDEX
    Explanations

    Mockery, dictionaries, dependency, names, data

    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
    èĽĽ
    -0.08
     alone
    -0.07
    ä¼ij
    -0.07
    alone
    -0.07
    empre
    -0.07
     ath
    -0.07
    åĮĸçī©
    -0.07
    bahn
    -0.06
    åĵªä¸Ģ个
    -0.06
    eniu
    -0.06
    POSITIVE LOGITS
    æıIJä¾Ľä¸ĢäºĽ
    0.07
     dictionaries
    0.07
    å°±æĺ¯æľī
    0.07
    èĽ®
    0.07
     somehow
    0.07
    ä¾Ľ
    0.07
    /logger
    0.07
    好çĶ¨
    0.06
    اء
    0.06
    aps
    0.06
    Activations Density 0.009%

    No Known Activations