© 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. 4266
    Prev
    Next
    INDEX
    Explanations

    synchronous DRAM

    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
    æŶæĬ¥
    -0.06
     ï
    -0.06
    abel
    -0.06
    abbr
    -0.06
    éĩĮ
    -0.06
    ä¿ŀ
    -0.06
    çķ¥
    -0.05
    ¬
    -0.05
     which
    -0.05
    ç½ijçļĦ
    -0.05
    POSITIVE LOGITS
    кеÑĢа
    0.08
    ignan
    0.08
    allen
    0.08
    itera
    0.08
    åºķä»·
    0.08
    ouston
    0.08
    bacher
    0.08
    以åıĬåħ¶ä»ĸ
    0.07
    ίδ
    0.07
    (PR
    0.07
    Activations Density 0.012%

    No Known Activations