© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51334
    Prev
    Next
    INDEX
    Explanations

    SQL queries with roles

    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
    ndo
    -0.09
    ç¤
    -0.09
    vall
    -0.08
    ndef
    -0.08
    nth
    -0.08
    estand
    -0.08
    为æĤ¨æݨèįIJ
    -0.08
    please
    -0.08
    龸éģĵ
    -0.08
    .orig
    -0.08
    POSITIVE LOGITS
    çģĮ
    0.06
    ACL
    0.06
    raph
    0.06
     rep
    0.06
    .emit
    0.06
    åľ¨ä¸Ĭè¿°
    0.06
     av
    0.06
    ä¸Ĭè¿°
    0.06
    0.06
    onaut
    0.06
    Activations Density 0.181%

    No Known Activations