© 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. 54992
    Prev
    Next
    INDEX
    Explanations

    web configuration

    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
    ovu
    -0.06
    æīĢ欲
    -0.06
    indi
    -0.06
     Downing
    -0.06
    æŦ
    -0.06
    ä¸įå®ĮçļĦ
    -0.06
    глÑıд
    -0.06
    缸åħ³çļĦ
    -0.05
     oneself
    -0.05
    isposable
    -0.05
    POSITIVE LOGITS
    çī¹çĤ¹æĺ¯
    0.09
    çī¹çĤ¹å°±æĺ¯
    0.08
    çļĦçī¹çĤ¹æĺ¯
    0.08
    loff
    0.08
    eks
    0.08
    udara
    0.08
    achs
    0.08
    vents
    0.08
    avs
    0.08
    uzz
    0.07
    Activations Density 0.212%

    No Known Activations