© 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. 55095
    Prev
    Next
    INDEX
    Explanations

    as indicated or directed

    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
    å¼Ħ
    -0.08
    ary
    -0.08
    agn
    -0.07
    .fun
    -0.07
    å¿ĥæĥĬ
    -0.07
     EDUCA
    -0.07
     Gastronom
    -0.07
     lẫn
    -0.07
    زاÙħ
    -0.07
    еÑģÑĤво
    -0.07
    POSITIVE LOGITS
    çļĨæľī
    0.08
    ัà¹Īà¸Ļ
    0.07
    ãģ«ãģ¤ãģį
    0.07
    æĤī
    0.06
    èµĦ
    0.06
    åıĤåĬłéĿ¢è¯ķ
    0.06
    trand
    0.06
    æĻ©
    0.06
    ired
    0.06
    çļĨ
    0.06
    Activations Density 0.955%

    No Known Activations