© 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. 6941
    Prev
    Next
    INDEX
    Explanations

    position: absolute;

    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
    Uvs
    -0.07
    çī¹å°Ķ
    -0.07
    omt
    -0.06
    çį
    -0.06
    éĨį
    -0.06
    ush
    -0.06
    åĪĽå»ºäºİ
    -0.06
     camp
    -0.06
     cylindrical
    -0.06
     miele
    -0.06
    POSITIVE LOGITS
    DataStream
    0.09
    Ĺı
    0.08
    ANDA
    0.08
     Rend
    0.07
    mano
    0.07
    ersch
    0.07
    ERR
    0.07
    -drop
    0.07
    ensee
    0.07
     Segu
    0.07
    Activations Density 0.001%

    No Known Activations