© 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. 16298
    Prev
    Next
    INDEX
    Explanations

    malfunction, diagnosis, contaminating

    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
     rather
    -0.07
    zust
    -0.07
    vall
    -0.07
    itest
    -0.07
    缸å½ĵ
    -0.07
     pretty
    -0.07
    åºĶå½ĵä¾Ŀçħ§
    -0.07
    æĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.07
    åĪĻåı¯ä»¥
    -0.07
    çŃ
    -0.07
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.12
    è¿ĩå¿«
    0.10
    è¿ĩ大
    0.10
     ÑģлÑĥÑĩайно
    0.10
    太大
    0.10
    too
    0.10
    è¿ĩå¤ļ
    0.09
    太å¤ļçļĦ
    0.09
    Too
    0.09
    太ä¹ħ
    0.09
    Activations Density 0.027%

    No Known Activations