© 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. 605
    Prev
    Next
    INDEX
    Explanations

    nuclear medicine, programming, technical terms

    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
    .call
    -0.07
    ubber
    -0.07
     cushion
    -0.06
    lish
    -0.06
    lesa
    -0.06
    ãĥŁãĥ¼
    -0.06
    жом
    -0.06
    irman
    -0.06
    aft
    -0.06
    Ø®ÙĪاÙĨ
    -0.06
    POSITIVE LOGITS
     bá»Ļi
    0.08
    atia
    0.07
    _PREFIX
    0.07
     Obl
    0.07
    åĽłåŃIJ
    0.07
    ÑģÑĤвен
    0.07
    -factor
    0.07
     cryptography
    0.07
    å¹³åĪĨ
    0.07
    天主æķĻ
    0.07
    Activations Density 0.002%

    No Known Activations