© 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. 10228
    Prev
    Next
    INDEX
    Explanations

    recent research attention

    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
    çļĦä¸ĢåĪĩéĥ½
    -0.09
    æºIJ头ä¸Ĭ
    -0.09
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.08
    åѦéĻ¢éĻ¢éķ¿
    -0.08
    ä¹ĭä¸Ģæĺ¯
    -0.08
    ç³»ç»Łå°Ĩ
    -0.08
    缺çĤ¹æĺ¯
    -0.07
    ä¸Ńå¿ĥçŃī
    -0.07
    orf
    -0.07
    ç»ĵæŀĦä¸Ń
    -0.07
    POSITIVE LOGITS
    ä¸įåĪ°äºĨ
    0.06
    çį
    0.06
    ä¹ĥèĩ³
    0.06
    isory
    0.06
    ly
    0.06
    aping
    0.06
    æīĢæľª
    0.06
    èĢĮåħ¶
    0.06
    èĢĮæĹłæ³ķ
    0.06
    ãĢĤ“
    0.06
    Activations Density 0.033%

    No Known Activations