© 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. 2306
    Prev
    Next
    INDEX
    Explanations

    logic and inference statements

    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
    benh
    -0.08
    æĹłå½¢
    -0.08
    ãģ¼ãģĨ
    -0.07
    ä¹ĺçĿĢ
    -0.07
    æłĩé«ĺ
    -0.07
    eros
    -0.07
    zah
    -0.07
    ĤŃ
    -0.07
    大æľī
    -0.07
    ç»·
    -0.06
    POSITIVE LOGITS
    ¬
    0.09
     ¬
    0.08
     inference
    0.08
    éŨåħ³
    0.08
     logic
    0.08
     conclus
    0.07
     truth
    0.07
    åľ¨è¿Ļ次
    0.07
    çļĦéĢ»è¾ij
    0.07
     fals
    0.07
    Activations Density 0.003%

    No Known Activations