© 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. 15383
    Prev
    Next
    INDEX
    Explanations

    phrase question is

    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
    NECT
    -0.08
    åºĶæľīçļĦè´¡çĮ®
    -0.08
    ä¹Łåı¯ä»¥æĺ¯
    -0.08
    èĢĮå·²
    -0.07
    »
    -0.07
    åħ¬è®¤
    -0.07
    usercontent
    -0.07
    åĵī
    -0.07
    ä¸ŃåĽ½ç«Ļ
    -0.07
    ciso
    -0.07
    POSITIVE LOGITS
    éĽĨä¸Ńåľ¨
    0.08
    æ¶īåıĬ
    0.07
    æĺ¯åħ³äºİ
    0.07
    èģļçĦ¦
    0.07
    åħ³äºİè¿Ľä¸ĢæŃ¥
    0.07
    åħ³äºİ
    0.07
    çļĦéĤ£ä¸ĢåĪ»
    0.07
     notwithstanding
    0.06
     regarding
    0.06
    äºĮä¸Ń
    0.06
    Activations Density 0.004%

    No Known Activations