© 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. 10032
    Prev
    Next
    INDEX
    Explanations

    german and necessarily

    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
    меÑģÑĤи
    -0.08
    ç«Ļç«Ļ
    -0.07
    ena
    -0.07
    coe
    -0.07
    åħ¬æīĢ
    -0.07
     Ø¥ÙĨÙĩ
    -0.07
    OnInit
    -0.07
    inting
    -0.07
    æķħåIJį
    -0.07
    atie
    -0.07
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.12
    ä¹Łéļıä¹ĭ
    0.11
    缸åºĶ
    0.10
    éļıä¹ĭ
    0.09
    缸åºĶçļĦ
    0.09
     necessarily
    0.09
    ä¹Łå¿ħé¡»
    0.09
    ä¹Łè·ŁçĿĢ
    0.09
    å¿ħçĦ¶æĺ¯
    0.09
     necesariamente
    0.08
    Activations Density 0.033%

    No Known Activations