© 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. 38306
    Prev
    Next
    INDEX
    Explanations

    academic research and development

    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
    æĢİä¹ĪåĬŀåij¢
    -0.08
    å®ŀè·µè¯ģæĺİ
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    Äĥng
    -0.07
     renom
    -0.07
    ãģªãĤĵãģ¨
    -0.07
    çļĦæīĭä¸Ń
    -0.06
    说äºĨç®Ĺ
    -0.06
     nowhere
    -0.06
    ä»Ģä¹Īéĥ½
    -0.06
    POSITIVE LOGITS
    æĥħåĨµåIJİ
    0.11
    æĥħåĨµåıĬ
    0.11
    以åıĬå¦Ĥä½ķ
    0.11
     ÙĪÙĥÙĬÙģ
    0.10
    åıĬåIJĦ
    0.10
    åıĬåħ¶
    0.10
    åıĬåħ¶åºĶçĶ¨
    0.10
     подÑĢобнее
    0.09
    å¦Ĥä½ķéĢļè¿ĩ
    0.09
    æĺ¯å¦Ĥä½ķ
    0.08
    Activations Density 0.187%

    No Known Activations