© 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. 59931
    Prev
    Next
    INDEX
    Explanations

    i.e

    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
    icur
    -0.09
    uret
    -0.08
    elpers
    -0.08
     comunque
    -0.08
    URT
    -0.08
     à¤ľà¥ģ
    -0.08
    UILTIN
    -0.08
    urious
    -0.08
    åĵ½
    -0.08
    angu
    -0.08
    POSITIVE LOGITS
     “
    0.08
    forth
    0.07
    ,
    0.06
     meaning
    0.06
    å°±æĺ¯è¯´
    0.06
     ‘
    0.06
     ones
    0.06
     siis
    0.06
    æĺ¯å°Ĩ
    0.06
     A
    0.06
    Activations Density 0.163%

    No Known Activations