© 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. 37908
    Prev
    Next
    INDEX
    Explanations

    demonstrate model building and running

    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
     overarching
    -0.07
    æĮĩå¼ķ
    -0.07
    士
    -0.06
    ä¸įçĶ±
    -0.06
    çĽĺçĤ¹
    -0.06
    åįİåĽ¾
    -0.06
    æĪĸèĢħ说
    -0.06
     (
    -0.06
     govern
    -0.06
    zte
    -0.06
    POSITIVE LOGITS
     experiment
    0.11
     Uncomment
    0.11
    experiment
    0.10
     Experiment
    0.10
     uncomment
    0.10
    Experiment
    0.10
    Python
    0.10
     Python
    0.10
    ç»ĵæŀľæĺ¾ç¤º
    0.10
     experimenting
    0.10
    Activations Density 0.064%

    No Known Activations