© 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. 750
    Prev
    Next
    INDEX
    Explanations

    firstly I

    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
    -0.08
    ä¸įäºĨå¤ļä¹ħ
    -0.08
    ije
    -0.08
    ija
    -0.07
    anes
    -0.07
    able
    -0.07
    ãģªãĤĬ
    -0.07
    arien
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    æĪĺ线
    -0.07
    POSITIVE LOGITS
    æĢĿæĥ³ä¸Ĭ
    0.07
    å§Ĺ
    0.07
     ÙĪÙĤبÙĦ
    0.07
    áŀī
    0.07
    æĬľãģį
    0.07
    krat
    0.07
    áĭ¨
    0.07
    minos
    0.06
    ìĶ©
    0.06
    ìĪľ
    0.06
    Activations Density 0.011%

    No Known Activations