© 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. 62310
    Prev
    Next
    INDEX
    Explanations

    points and circles 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
    ÑħÑĢо
    -0.07
    çĨ¬
    -0.07
    å±Ģåľ°
    -0.07
    åĨ²è¿Ľ
    -0.07
    è¿Ļåĩł
    -0.07
     Amend
    -0.07
    _conversion
    -0.07
    å¼ĢåĽ½
    -0.06
    .Flush
    -0.06
    é£ŀè·ĥ
    -0.06
    POSITIVE LOGITS
    ä»»æĦı
    0.09
     points
    0.08
    ä¸įåIJĮæŶ
    0.08
    Patr
    0.07
    patr
    0.07
    -points
    0.07
     arbitrary
    0.07
    ä½įç½®çļĦ
    0.07
    å¿ĺè¿Ķ
    0.07
    ä¸įåģľçļĦ
    0.07
    Activations Density 0.006%

    No Known Activations