© 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. 61441
    Prev
    Next
    INDEX
    Explanations

    physical examination findings

    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
    å°ģ顶
    -0.09
    ersh
    -0.08
    ä¼ijçľł
    -0.07
    urus
    -0.07
    çĺĭ
    -0.07
    ä¸ŃéĢĶ
    -0.07
    çļĦæĸ°åŀĭ
    -0.07
    åIJĪçIJĨè§ĦåĪĴ
    -0.07
     destined
    -0.07
    çŃīéĩį大
    -0.07
    POSITIVE LOGITS
     оÑģмоÑĤÑĢа
    0.10
     оÑģмоÑĤÑĢ
    0.10
     assessment
    0.09
     observations
    0.09
    åĪĿæŃ¥
    0.09
     palp
    0.09
    è§Ĥå¯Ł
    0.09
     clues
    0.09
    第ä¸Ģåį°è±¡
    0.09
    è¯Ħä¼°
    0.08
    Activations Density 0.163%

    No Known Activations