© 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. 47833
    Prev
    Next
    INDEX
    Explanations

    contrasting or comparing clauses

    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
    ãĤ¤ãĥĦ
    -0.08
    åı£éķĩ
    -0.07
    ÃŁe
    -0.07
    ಡಿ
    -0.07
    antha
    -0.07
    åħ°çī¹
    -0.07
    åħ·æľīä¸Ģå®ļ
    -0.07
    &&(
    -0.07
     Caught
    -0.07
    æĹłè¯Ń
    -0.07
    POSITIVE LOGITS
    åĮºåĪ«äºİ
    0.15
    ä¸įåIJĮäºİ
    0.13
     versus
    0.13
    vs
    0.13
     vs
    0.13
    缸æ¯Ķäºİ
    0.12
    èĢĮéĿŀ
    0.12
     compared
    0.12
    èĢĮä¸įæĺ¯
    0.11
     unlike
    0.11
    Activations Density 0.417%

    No Known Activations