© 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. 63049
    Prev
    Next
    INDEX
    Explanations

    list format `)`

    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
    utz
    -0.08
    åħ¶å®ŀåľ¨
    -0.07
    utzer
    -0.07
    åħ¬åı¸æ³¨åĨĮ
    -0.07
    TypeId
    -0.07
    à¹ģ
    -0.07
    ynch
    -0.07
    λλη
    -0.07
    ync
    -0.07
    esti
    -0.06
    POSITIVE LOGITS
     format
    0.09
     representing
    0.08
    æł¼å¼ı
    0.08
    represent
    0.08
    enius
    0.08
    ä¾ĭå¦Ĥ
    0.07
    ibas
    0.07
     represents
    0.07
    代表
    0.07
    å½¢å¼ı
    0.07
    Activations Density 0.057%

    No Known Activations