© 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. 41754
    Prev
    Next
    INDEX
    Explanations

    here / aqui / nonlocal words

    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
     ens
    -0.08
    å°±åºĶ该
    -0.07
    ulon
    -0.07
     indeed
    -0.07
    ä¸įä»ħèĥ½å¤Ł
    -0.06
    èĪĴ
    -0.06
    ä¹ŁåºĶ该
    -0.06
    ä¸įåºĶ该
    -0.06
    ç»Ŀ对ä¸įèĥ½
    -0.06
    å®ĺæĸ¹å¾®ä¿¡
    -0.06
    POSITIVE LOGITS
     here
    0.10
     aqui
    0.10
     ÙĩÙĨا
    0.10
    here
    0.09
     disini
    0.09
     ÑģÑİда
    0.09
     aquÃŃ
    0.09
    à¸ĺิ
    0.08
    åľ¨éĢĻ裡
    0.08
    éĥ½åľ¨è¿ĻéĩĮ
    0.08
    Activations Density 0.043%

    No Known Activations