© 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. 54946
    Prev
    Next
    INDEX
    Explanations

    "past"

    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
    ectu
    -0.07
    ohlen
    -0.07
     Hulu
    -0.07
    çļĦ身ä¸Ĭ
    -0.07
    碰
    -0.07
    çİ·
    -0.07
    æľīä¸Ģç§į
    -0.07
    leos
    -0.07
    icide
    -0.07
    actories
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵåĨħ容
    0.09
    åħ·ä½ĵ
    0.09
    æĭ¬
    0.08
     followed
    0.08
     заÑĤем
    0.07
    åĪĹ举
    0.07
    (...)
    0.07
    çļĦåħ·ä½ĵ
    0.07
     (...)
    0.07
    çĦ¶åIJİ
    0.07
    Activations Density 0.206%

    No Known Activations