© 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. 4581
    Prev
    Next
    INDEX
    Explanations

    assessed or measured values

    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
    ovel
    -0.07
     Conti
    -0.07
     그를
    -0.07
    icola
    -0.07
    onos
    -0.07
    รวà¸Ķ
    -0.07
    个æĪĸå¤ļ个
    -0.07
    åĽ½åĬ¡
    -0.07
     Paci
    -0.07
    Extras
    -0.06
    POSITIVE LOGITS
     tracked
    0.08
     surveyed
    0.07
     sampled
    0.07
     assessed
    0.07
    orch
    0.07
     insgesamt
    0.07
    æĥ
    0.07
     averaged
    0.06
     (%)
    0.06
    æŀĹåŃIJ
    0.06
    Activations Density 0.020%

    No Known Activations