© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55075
    Prev
    Next
    INDEX
    Explanations

    archaic phrasing like thou

    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
    Negative Logits
     basically
    -0.09
    æīĢè°ĵçļĦ
    -0.08
     Basically
    -0.08
    åŁºæľ¬ä¸Ĭ
    -0.08
    èĮģ
    -0.08
    ynn
    -0.08
    ÑģÑĤÑĢÑı
    -0.08
    å±ģèĤ¡
    -0.08
     ÑıкобÑĭ
    -0.07
    Basically
    -0.07
    POSITIVE LOGITS
    æļĤ
    0.08
    åįĥä¸ĩ
    0.08
    äºĶèī²
    0.07
     millions
    0.07
     pant
    0.07
     beside
    0.07
     инÑĭе
    0.07
    lder
    0.07
     mighty
    0.06
    ÑĮе
    0.06
    Activations Density 0.218%

    No Known Activations