© 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. 3931
    Prev
    Next
    INDEX
    Explanations

    vs distinction

    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
    èĩªçĦ¶ä¸įä¼ļ
    -0.07
    WSC
    -0.07
    å¿ĺä¸įäºĨ
    -0.07
    XR
    -0.07
    æ²ĥ
    -0.07
    anty
    -0.07
     boc
    -0.07
    缸å¾ħ
    -0.07
    æĪĸåħ¶ä»ĸ
    -0.07
    å®ģåİ¿
    -0.07
    POSITIVE LOGITS
    åĮºåĪ«äºİ
    0.12
    çļĦåĮºåĪ«
    0.10
     distinction
    0.10
     vs
    0.10
    ä¸įåIJĮäºİ
    0.09
    æĮĩ
    0.09
    æĺ¯æĮĩ
    0.09
    çļĦå®ļä¹ī
    0.08
     differs
    0.08
    åĮºåĪ«
    0.08
    Activations Density 0.212%

    No Known Activations