© 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. 4906
    Prev
    Next
    INDEX
    Explanations

    processes and procedures

    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
    éĥ½åıªæĺ¯
    -0.07
     DID
    -0.06
     intr
    -0.06
    tid
    -0.06
    tas
    -0.06
     handful
    -0.06
    å®ĥå°±æĺ¯
    -0.06
    è¿Ļå°±æĺ¯
    -0.06
    大å°ıçļĦ
    -0.06
    éĥ½åĥı
    -0.06
    POSITIVE LOGITS
    çļĦçī¹çĤ¹æĺ¯
    0.10
    åĨħ容åĮħæĭ¬
    0.09
    ouden
    0.09
    abei
    0.09
     totiž
    0.09
    ç²ªæ±ł
    0.08
    çī¹çĤ¹æĺ¯
    0.08
     nemlig
    0.08
    !!:
    0.08
     ÑıкобÑĭ
    0.08
    Activations Density 1.613%

    No Known Activations