© 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. 60018
    Prev
    Next
    INDEX
    Explanations

    killed by, spill, seventy

    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
    çīĽ
    -0.06
    ogg
    -0.06
    족
    -0.06
    ä»»
    -0.06
    æīİ
    -0.06
     Dalle
    -0.06
    -feedback
    -0.06
    enskap
    -0.06
    壮çļĦ
    -0.06
    ogs
    -0.06
    POSITIVE LOGITS
     somewhere
    0.08
    æŁIJä¸Ģ
    0.08
    æŁIJ个
    0.08
    æŁIJä¸Ģ个
    0.08
    æŁIJåĢĭ
    0.08
    iets
    0.08
    æŁIJç§į
    0.08
    hares
    0.08
     ÑıкобÑĭ
    0.07
    ABCDEFG
    0.07
    Activations Density 0.016%

    No Known Activations