© 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. 55097
    Prev
    Next
    INDEX
    Explanations

    latex fraction syntax

    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
    вел
    -0.07
    оÑĤе
    -0.07
    weit
    -0.07
    ingly
    -0.06
     Ñģобой
    -0.06
    ä¸İä¼Ĺ
    -0.06
    iot
    -0.06
    iong
    -0.06
    arius
    -0.06
    äºĮåįģä¸ĥ
    -0.06
    POSITIVE LOGITS
    alloween
    0.09
    illons
    0.08
    llum
    0.08
    à¸Ľà¸£à¸´
    0.07
    .overflow
    0.07
    ìłĦìŀ¬
    0.07
     bumped
    0.07
    Ïĥιά
    0.07
    IPA
    0.07
    åħ´éļĨ
    0.07
    Activations Density 0.003%

    No Known Activations