© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48788
    Prev
    Next
    INDEX
    Explanations

    expressing possibility or differing opinions

    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
    å¾Īåı¯èĥ½æĺ¯
    -0.09
    å¦Ĥåħ¶
    -0.08
    å»ĵ
    -0.08
    TypeInfo
    -0.08
     wherever
    -0.08
    éĿŀ常éĢĤåIJĪ
    -0.07
     cụ
    -0.07
    arb
    -0.07
    URED
    -0.07
    å¾Īåı¯èĥ½
    -0.07
    POSITIVE LOGITS
    认为
    0.11
     incorrectly
    0.09
    ä¼ļè§īå¾Ĺ
    0.09
     rightly
    0.09
    认为æĺ¯
    0.08
     incorrect
    0.08
    注æĦıçļĦæĺ¯
    0.08
     mistaken
    0.08
     argue
    0.08
     errone
    0.07
    Activations Density 0.018%

    No Known Activations