© 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. 12650
    Prev
    Next
    INDEX
    Explanations

    caspase, damaged DNA, lower jaw

    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
    ä»·æł¼æĺ¯
    -0.07
    å¹´çļĦæŶåĢĻ
    -0.07
    æ´»åĬ¨æŶ
    -0.07
    人äºĨ
    -0.07
    æ°´æĺ¯
    -0.06
    åħ·ä½ĵæĥħåĨµ
    -0.06
    ëł¥ìĿĢ
    -0.06
    âĤ¬,
    -0.06
     tev
    -0.06
     ëĵ±ìĿĢ
    -0.06
    POSITIVE LOGITS
    ä¼ļè®®åı¬å¼Ģ
    0.12
    éĹ®é¢ĺåĪĨæŀIJ
    0.10
    åı¥è¯Ŀ说
    0.09
    人被
    0.08
    äºĭæķħåıijçĶŁ
    0.08
    )::
    0.08
    >::
    0.08
    話說
    0.08
    è¯Ŀ说
    0.08
    StateChanged
    0.08
    Activations Density 0.248%

    No Known Activations