© 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. 33326
    Prev
    Next
    INDEX
    Explanations

    second, third, fourth, etc

    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
    æľī好
    -0.07
    çĻ½å±±
    -0.07
    umbo
    -0.06
    ç±³äºļ
    -0.06
    çĶļèĩ³æĺ¯
    -0.06
    rost
    -0.06
    æı´
    -0.06
    umul
    -0.06
    å¯ĮåĬĽ
    -0.06
    aption
    -0.06
    POSITIVE LOGITS
    åIJĮæł·
    0.10
    Similarly
    0.09
     similarly
    0.09
     Similarly
    0.09
    åıĪå¦Ĥ
    0.09
    åIJĮçIJĨ
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.08
    igham
    0.08
    [dir
    0.08
    åĶ®ä»·ä¸º
    0.08
    Activations Density 0.025%

    No Known Activations