© 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. 7176
    Prev
    Next
    INDEX
    Explanations

    improved Slashdot

    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
     bizar
    -0.07
    带åĽŀ家
    -0.07
    деб
    -0.07
    ÑĢга
    -0.07
    umar
    -0.07
    .blog
    -0.06
    åįļ
    -0.06
    éŨéĿ¢
    -0.06
    çĪ±ç¾İ
    -0.06
    oku
    -0.06
    POSITIVE LOGITS
    Ŀ
    0.07
    ä¹ĭäºĭ
    0.07
    ikk
    0.07
    º
    0.07
    coes
    0.06
    ä¹İåħ¶
    0.06
    èĪĮå°ĸä¸ĬçļĦ
    0.06
    å´½
    0.06
    ä¹ĭ声
    0.06
     Abbott
    0.06
    Activations Density 0.678%

    No Known Activations