© 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. 33375
    Prev
    Next
    INDEX
    Explanations

    make or take

    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
    ãĤ¸ãĤ¢
    -0.07
    uing
    -0.07
    ruhe
    -0.06
    å¤ļæݪ并举
    -0.06
    ominator
    -0.06
    оÑĢод
    -0.06
    æľīè°ģ
    -0.06
    cando
    -0.06
     Bash
    -0.06
     ÑģамомÑĥ
    -0.06
    POSITIVE LOGITS
     considerable
    0.08
    ÑģÑĮ
    0.08
    phasis
    0.07
    attes
    0.07
    ä¸įå°ıçļĦ
    0.07
    ণ
    0.07
    anii
    0.07
    ÑģÑı
    0.07
     itself
    0.07
    笤
    0.07
    Activations Density 0.627%

    No Known Activations