© 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. 23126
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculation

    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
     beide
    -0.13
     обоиÑħ
    -0.12
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    -0.12
     beiden
    -0.12
     оба
    -0.12
    à¸Ĺัà¹īà¸ĩà¸Ħูà¹Ī
    -0.11
     दà¥ĭनà¥ĭà¤Ĥ
    -0.11
     Beide
    -0.11
     Ðŀба
    -0.11
     begge
    -0.11
    POSITIVE LOGITS
    ä¸īèĢħ
    0.15
    è¿Ļä¸ī个
    0.15
    è¿Ļä¸īç§į
    0.14
    è¿Ļä¸ī
    0.14
    è¿ĻåĽĽä¸ª
    0.13
    åīįä¸ī
    0.12
    ä¸īæĸ¹
    0.12
    ä¸ī项
    0.12
    ä¸īæĸ¹éĿ¢
    0.11
    ä¸īéĩį
    0.11
    Activations Density 0.012%

    No Known Activations