© 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. 22360
    Prev
    Next
    INDEX
    Explanations

    medical conditions and demographics

    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
    à¹ĥหà¹īà¸Ħวาม
    -0.07
    äºijéľĦ
    -0.07
    osing
    -0.07
    ativamente
    -0.07
    级
    -0.07
    浩çī¹
    -0.07
    èįŁèIJĥ
    -0.07
     Rohr
    -0.07
    -Sah
    -0.07
    ella
    -0.07
    POSITIVE LOGITS
    åĩĨæŶ
    0.07
    æĹłä»»ä½ķ
    0.06
    èĥ½å¯¹
    0.06
    alon
    0.06
    MinMax
    0.06
    ack
    0.06
    airo
    0.06
     Ingr
    0.06
    综åIJĪåĪĨæŀIJ
    0.06
    åijĹ
    0.06
    Activations Density 0.004%

    No Known Activations