© 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. 44286
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    æķĻèĤ²åİħ
    -0.07
     ÙĦÙĤ
    -0.07
    åı¯æ¢¦
    -0.07
    omis
    -0.06
    .sul
    -0.06
    _UNIQUE
    -0.06
    llvm
    -0.06
     Freib
    -0.06
    èĨ
    -0.06
    çłĤæľº
    -0.06
    POSITIVE LOGITS
    quared
    0.08
    ingers
    0.08
    Squared
    0.08
    agog
    0.08
    æĭīå¾·
    0.07
    amenta
    0.07
    ampions
    0.07
    产åĵģä»·æł¼
    0.07
    zag
    0.07
    adoo
    0.07
    Activations Density 0.002%

    No Known Activations