© 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. 55035
    Prev
    Next
    INDEX
    Explanations

    list elements

    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
    æĪ¶
    -0.08
    åħĥåĪ°
    -0.07
    æĭīå¾·
    -0.07
    inga
    -0.07
    çļĦå°±
    -0.06
    IGO
    -0.06
    ÙĬب
    -0.06
    ¤íĥ
    -0.06
    áĢĻáĢºáĢ¸
    -0.06
    .currentTarget
    -0.06
    POSITIVE LOGITS
    partials
    0.07
    inding
    0.07
     Downs
    0.07
    ä¸įåĢ¦
    0.07
    æĹłçĶ¨
    0.07
    ä¸įèĥľ
    0.07
    stial
    0.07
    _FUN
    0.06
    Thr
    0.06
     constant
    0.06
    Activations Density 0.003%

    No Known Activations