© 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. 28511
    Prev
    Next
    INDEX
    Explanations

    optimization and solutions

    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
    odo
    -0.07
    ä¸įå¼ĢçļĦ
    -0.07
    elin
    -0.07
     clickable
    -0.07
    æ±ĤçĶŁåŃĺ
    -0.06
    å¼ĢèĢĥ
    -0.06
    [count
    -0.06
    allas
    -0.06
    UPPORTED
    -0.06
    metro
    -0.06
    POSITIVE LOGITS
    迹
    0.08
    osit
    0.08
    wah
    0.08
    ypi
    0.08
    åıªè¦ģä¸Ģ
    0.07
    esis
    0.07
    ä¸įåĬ¨æijĩ
    0.07
    rov
    0.07
    ë¡Ŀ
    0.07
    ertet
    0.07
    Activations Density 0.002%

    No Known Activations