© 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. 4322
    Prev
    Next
    INDEX
    Explanations

    towns and villages

    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
    家äºĭ
    -0.09
     Piemonte
    -0.08
    è·Łäºº
    -0.07
    ãĤ¤ãĥĻ
    -0.07
    ä¸įå¹³
    -0.07
    æ´ŀåºŃ
    -0.07
    åĮħåİ¢
    -0.06
    横æī«
    -0.06
    onus
    -0.06
    æĻ¯åįĢ
    -0.06
    POSITIVE LOGITS
    åıĬåij¨è¾¹
    0.09
    å§ĭ建äºİ
    0.09
    æĹ¥è®¯
    0.08
    éİ®
    0.08
    åĽ½éĻħåĮĸçļĦ
    0.08
    å±ħæ°ij
    0.08
    建åĪ¶
    0.08
    _FALL
    0.08
     enclave
    0.08
     administr
    0.08
    Activations Density 0.687%

    No Known Activations