© 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. 34933
    Prev
    Next
    INDEX
    Explanations

    version pre-release tags

    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
    åģĩå±±
    -0.07
    .DO
    -0.07
    igno
    -0.06
     há»Ļ
    -0.06
     Shakespe
    -0.06
    .scrollTop
    -0.06
     mÃły
    -0.06
     Sieg
    -0.06
     Poker
    -0.06
    wor
    -0.06
    POSITIVE LOGITS
    latest
    0.11
     latest
    0.09
    edImage
    0.09
    .latest
    0.08
    _latest
    0.08
    æľĢæĸ°çļĦ
    0.08
    æľĢæĸ°çīĪæľ¬
    0.08
    Latest
    0.08
    çļĦæľĢæĸ°
    0.08
    Compatible
    0.08
    Activations Density 0.289%

    No Known Activations