© 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. 59977
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    éĢļ天
    -0.07
    zijd
    -0.06
    agy
    -0.06
    ä¸įä¼ļ对
    -0.06
    ãĥ¬ãĥ³ãĥĢãĥ¼
    -0.06
     Bent
    -0.06
    (po
    -0.06
    _REGS
    -0.06
    ä¸įä¼ļ被
    -0.06
    nte
    -0.06
    POSITIVE LOGITS
    odor
    0.08
    åĬłæĭ¿å¤§
    0.08
    ãģ±
    0.07
    urst
    0.07
    ponce
    0.07
    iksi
    0.07
    ussy
    0.07
    пÑĤа
    0.07
    Ñīенко
    0.07
    å¤į
    0.07
    Activations Density 0.001%

    No Known Activations