© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30066
    Prev
    Next
    INDEX
    Explanations

    package name marker

    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
    waran
    -0.07
    osit
    -0.07
    èIJ½èĬ±
    -0.06
    ocrates
    -0.06
    rets
    -0.06
    ç¿ĺ
    -0.06
    åİ¢
    -0.06
    icit
    -0.06
    è¿ĶåĽŀåĪĹ表
    -0.06
    DIRECTORY
    -0.06
    POSITIVE LOGITS
    enton
    0.08
    åıĹäºĨ
    0.07
    aylor
    0.07
    gern
    0.07
    cont
    0.06
    que
    0.06
    ä¸įçŁ¥éģĵ
    0.06
    DataStream
    0.06
    ContentSize
    0.06
    æµ®
    0.06
    Activations Density 0.089%

    No Known Activations