© 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. 31618
    Prev
    Next
    INDEX
    Explanations

    percentages or discounts

    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
     homo
    -0.07
     emp
    -0.06
    los
    -0.06
     Marino
    -0.06
     Emp
    -0.06
    imon
    -0.06
    lever
    -0.06
    documentation
    -0.06
     sym
    -0.06
    æ·±åħ¥å®ŀæĸ½
    -0.06
    POSITIVE LOGITS
     rounded
    0.11
    rounded
    0.10
     capped
    0.09
     rounding
    0.09
    åºĶå°½éĩı
    0.09
    .ceil
    0.08
    eger
    0.08
     تÙĤرÙĬب
    0.08
     moderated
    0.08
    åı¯èĥ½ä¼ļåĩºçİ°
    0.08
    Activations Density 0.040%

    No Known Activations