© 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. 58219
    Prev
    Next
    INDEX
    Explanations

    GM, OE, ran, went, remains

    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
    å¾·åįİ
    -0.06
    çļĦèĩªå·±
    -0.06
    åľ°çľĭçĿĢ
    -0.06
    alh
    -0.06
    ä¼ģä¸ļ主
    -0.06
    áng
    -0.06
    人ä¹ĭ
    -0.06
    åĵĪ
    -0.06
    åīįåĪĹ
    -0.06
    ÑĪаÑĤ
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶
    0.09
    åıĬåħ¶
    0.09
    à¹Ģà¸Ńà¸ĩ
    0.08
    ilton
    0.08
    æīĢå¤ĦçļĦ
    0.08
    åĩŃåĢŁåħ¶
    0.07
    çļĦé«ĺçŃī
    0.07
    arei
    0.07
    ä¹ĭèĬ±
    0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    0.07
    Activations Density 0.079%

    No Known Activations