© 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. 51062
    Prev
    Next
    INDEX
    Explanations

    rates, averages, or amounts

    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
    èĻIJ
    -0.07
    olist
    -0.07
    orque
    -0.07
     whenever
    -0.06
    çľĭä¼¼
    -0.06
    hape
    -0.06
    hlak
    -0.06
     недоÑģÑĤа
    -0.06
    atk
    -0.06
    èĵ¬èݱ
    -0.06
    POSITIVE LOGITS
     average
    0.11
     averages
    0.10
    çļĦå¹³åĿĩ
    0.10
    å¹³åĿĩ
    0.10
    å¹³åĿĩåĢ¼
    0.10
     beträgt
    0.10
    大约æĺ¯
    0.09
    ä¸ĢèĪ¬åľ¨
    0.09
    ä¸ĢèĪ¬ä¸º
    0.09
     typical
    0.09
    Activations Density 0.066%

    No Known Activations