© 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. 48963
    Prev
    Next
    INDEX
    Explanations

    contrast conjunctions

    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
    gd
    -0.08
    æŀ¶
    -0.07
    erville
    -0.07
    ency
    -0.07
    æ§Ľ
    -0.07
     Anyway
    -0.07
    æĤī
    -0.07
    éļı
    -0.07
    è¦ģ好好
    -0.06
    çĦ¶
    -0.06
    POSITIVE LOGITS
    å®ŀåľ¨æĺ¯å¤ª
    0.08
    λη
    0.07
    éļ¾éģĵæĺ¯
    0.07
    æĺ¯ä¸įæĺ¯
    0.07
    åı¯èĥ½æĺ¯åĽłä¸º
    0.07
     IsNot
    0.07
    åĨįçľĭçľĭ
    0.07
    éļ¾éģĵ
    0.07
    ordat
    0.07
     à¤ķà¥įयà¥ĭà¤Ĥ
    0.07
    Activations Density 0.018%

    No Known Activations