© 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. 22492
    Prev
    Next
    INDEX
    Explanations

    plane Geometry

    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
    ylon
    -0.07
    表éĿ¢
    -0.07
    æŃĮ声
    -0.07
     Haf
    -0.07
    kers
    -0.07
    åģľä¸ĭ
    -0.07
    ä¹īåĬ¡æķĻèĤ²éĺ¶æ®µ
    -0.07
    ibar
    -0.07
    èĶĵ
    -0.07
    dba
    -0.07
    POSITIVE LOGITS
    åĮħåIJ«äºĨ
    0.07
     traz
    0.07
    thy
    0.07
     containing
    0.07
    .fixture
    0.07
    enge
    0.07
    ä¸ŃçļĦæīĢæľī
    0.07
    isir
    0.06
    示èĮĥé¡¹çĽ®
    0.06
    .only
    0.06
    Activations Density 0.007%

    No Known Activations