© 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. 52190
    Prev
    Next
    INDEX
    Explanations

    .toString and .models

    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
    erate
    -0.07
    icino
    -0.07
    çĶ¨æľĢ
    -0.07
    æĨĶæĤ´
    -0.07
    常常ä¼ļ
    -0.07
     empre
    -0.07
    åĪ°çĽ®åīį
    -0.06
    举个ä¾ĭåŃIJ
    -0.06
    pan
    -0.06
    èĥ½å¯¹
    -0.06
    POSITIVE LOGITS
    à¸Ħืà¸Ń
    0.07
    GenerationStrategy
    0.07
     ialah
    0.07
    udiant
    0.07
    baut
    0.06
    omi
    0.06
    åį³ä¸º
    0.06
    authent
    0.06
    åĪĨåĪ«ä¸º
    0.06
    rett
    0.06
    Activations Density 0.002%

    No Known Activations