© 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. 11572
    Prev
    Next
    INDEX
    Explanations

    while connecting 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
    ä½Ĩä¸įéĻIJäºİ
    -0.12
     vs
    -0.08
    èĢĮæĺ¯ä¸Ģ个
    -0.07
     zwar
    -0.07
    auer
    -0.07
    èĢĮä½ł
    -0.07
    áÅĻ
    -0.07
    æĿ¥è¯´
    -0.07
     while
    -0.07
    ä¸įä»ħåľ¨
    -0.06
    POSITIVE LOGITS
    ä¿ĿæĮģçĿĢ
    0.08
    .pp
    0.07
    ä¿ĿæĮģ稳å®ļ
    0.07
    ä¿ĿæĮģåľ¨
    0.07
    å§ĭç»Īä¿ĿæĮģ
    0.07
    ÙĪØ«
    0.07
     Ñįлем
    0.07
     simultaneously
    0.07
    owing
    0.07
    aneously
    0.07
    Activations Density 0.034%

    No Known Activations