© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63791
    Prev
    Next
    INDEX
    Explanations

    medical and scientific journals

    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
    强度çļĦ
    -0.09
    强度åĴĮ
    -0.08
    å¾ĭ
    -0.08
    强度
    -0.07
    ToWorld
    -0.07
    density
    -0.07
    ertet
    -0.07
    ostro
    -0.07
    åı©
    -0.07
    anyl
    -0.07
    POSITIVE LOGITS
    å£ĩ
    0.08
    -names
    0.07
    èĴIJ
    0.07
     Rak
    0.06
    è¡·
    0.06
     lengths
    0.06
    æĹ¥æŃ¢
    0.06
    ä¸Ģæĭ³
    0.06
     INTERVAL
    0.06
    å±Ĥé«ĺ
    0.06
    Activations Density 0.010%

    No Known Activations