© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29973
    Prev
    Next
    INDEX
    Explanations

    other, joint, times

    np_acts-logits-general · gemini-2.5-flash-lite

    words indicating temporal or contextual similarity, particularly "as" and phrases comparing one thing to another.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
     Tow
    -0.08
    è¿ĺåı¯
    -0.08
     hallmark
    -0.08
     via
    -0.08
     Likewise
    -0.08
     toward
    -0.08
     famed
    -0.07
    uktion
    -0.07
    åħ¼åħ·
    -0.07
     décor
    -0.07
    POSITIVE LOGITS
    æ¶īåıĬåĪ°
    0.11
    åı¯èĥ½ä¼ļ对
    0.10
    åı¯èĥ½ä¼ļæľī
    0.10
    åı¯èĥ½ä¼ļ导èĩ´
    0.10
    éļıçĿĢæŶéĹ´çļĦæݨ移
    0.10
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    0.09
    并éĿŀæĺ¯
    0.09
     letzt
    0.09
    ä¸įåºĶ该
    0.09
    åľ¨è¿Ļ个è¿ĩç¨ĭä¸Ń
    0.08
    Activations Density 0.007%

    No Known Activations