© 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. 55260
    Prev
    Next
    INDEX
    Explanations

    dual or mirror symmetry

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ilt
    -0.07
    raga
    -0.06
    apan
    -0.06
    è°£
    -0.06
    nee
    -0.06
    ocratic
    -0.06
    fras
    -0.06
    agt
    -0.06
    ålet
    -0.06
    éĺ»æĮ¡
    -0.06
    POSITIVE LOGITS
    haupt
    0.08
    hipster
    0.08
    ÑĤоÑĢи
    0.07
    ine
    0.07
     thereof
    0.07
    aris
    0.07
    ungeons
    0.07
    uplicated
    0.07
    roit
    0.07
     counterparts
    0.07
    Activations Density 0.005%

    No Known Activations