© 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. 37434
    Prev
    Next
    INDEX
    Explanations

    organization structure redesign districts

    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
    ruc
    -0.08
     Midd
    -0.07
    паÑģ
    -0.07
     impro
    -0.07
    .Be
    -0.07
    damage
    -0.07
    åIJĮèĥŀ
    -0.07
    pä
    -0.07
    ä»ĸ们çĶ¨
    -0.07
    dirty
    -0.07
    POSITIVE LOGITS
    åĪĴåĪĨ
    0.11
    èģĮèĥ½
    0.10
    ç²¾ç®Ģ
    0.10
     decentral
    0.10
    æīģå¹³
    0.10
    æĭĨåĪĨ
    0.09
    éļ¶å±ŀ
    0.09
     redundant
    0.09
    åĪĴ
    0.09
     restructuring
    0.08
    Activations Density 0.040%

    No Known Activations