© 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. 4739
    Prev
    Next
    INDEX
    Explanations

    pale yellow

    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
    antum
    -0.08
    æĪijè¦ģè¯Ħ论
    -0.07
    atera
    -0.07
    åĽŀéģĵ
    -0.07
    åĵ½
    -0.07
    ç²īçļĦ
    -0.07
    çĶŁç´ł
    -0.07
    æıIJç¥ŀ
    -0.07
    rogram
    -0.07
    ade
    -0.07
    POSITIVE LOGITS
    沸çĤ¹
    0.07
    ŀ
    0.07
    çĨĶçĤ¹
    0.07
    æ¯ĴæĢ§
    0.06
    éļı
    0.06
    éłĨ
    0.06
    ìłij
    0.06
     mister
    0.06
    è¾ij
    0.06
    顺
    0.06
    Activations Density 0.004%

    No Known Activations