© 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. 50912
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and symbols

    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
    erring
    -0.08
    èĬĻ
    -0.07
    æģĭ人
    -0.07
    åĿŁ
    -0.07
    åĹ£
    -0.06
    ÑĦеÑĢа
    -0.06
    对æĪij说
    -0.06
    PT
    -0.06
    Marks
    -0.06
    áŀĩ
    -0.06
    POSITIVE LOGITS
    åĨįåĬł
    0.09
    èĥ³
    0.08
    åĬłèµ·æĿ¥
    0.08
    èĩªå·±éĥ½
    0.08
    etar
    0.08
    ëį°
    0.07
    åĨįåĬłä¸Ĭ
    0.07
    åĨįæİ¥
    0.07
    ลฯ
    0.07
    管çIJĨçŃī
    0.07
    Activations Density 0.002%

    No Known Activations