© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 33359
    Prev
    Next
    INDEX
    Explanations

    moral equivalence

    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
    æĹ©èµ·
    -0.08
    èĦļè¸ıå®ŀåľ°
    -0.08
    çī¢è®°ä½¿åij½
    -0.07
    è°¢ç»Ŀ
    -0.07
    ä¸¥æł¼è¦ģæ±Ĥ
    -0.07
     crisp
    -0.07
    åºĦéķĩ
    -0.07
    æĹłç¼ĺ
    -0.07
     maj
    -0.07
    æĴµ
    -0.07
    POSITIVE LOGITS
    容å¿į
    0.12
     tolerated
    0.11
    妥åįı
    0.11
     toler
    0.11
     tolerate
    0.10
    åħģ许
    0.10
    åIJĪçIJĨåĮĸ
    0.10
     looph
    0.10
     tolerance
    0.10
     tolerant
    0.10
    Activations Density 0.276%

    No Known Activations