© 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. 11351
    Prev
    Next
    INDEX
    Explanations

    Pope Clement

    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
    jal
    -0.08
    羯
    -0.07
    åľ¨åݻ年
    -0.07
    åĿĩåľ¨
    -0.07
    azzo
    -0.07
     اÙĦÙħض
    -0.07
     зада
    -0.07
    endoza
    -0.07
    天æŶ
    -0.07
    å®ļæľŁè¿Ľè¡Į
    -0.07
    POSITIVE LOGITS
    éĤ£æŶ
    0.11
    æѤæŶ
    0.10
    è¿Ļä¸Ģå¹´
    0.09
    éĤ£æŶåĢĻ
    0.09
    è¿Ļ个æŶåĢĻ
    0.08
    è¿ĻæŶ
    0.08
    æѤæĻĤ
    0.08
    æѤæŶçļĦ
    0.08
    å½ĵæŶ
    0.08
    éĤ£æŶçļĦ
    0.08
    Activations Density 0.832%

    No Known Activations