© 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. 59046
    Prev
    Next
    INDEX
    Explanations

    input followed by output or response

    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
    ighted
    -0.09
    ลฯ
    -0.08
    emente
    -0.08
    ãĢħãģ¨
    -0.08
    ification
    -0.08
    wares
    -0.07
    ëģĶ
    -0.07
    à¦ĸানà§ĩ
    -0.07
    utine
    -0.07
    ibal
    -0.07
    POSITIVE LOGITS
    /output
    0.14
    -output
    0.10
    ting
    0.09
    /out
    0.09
    ted
    0.08
    most
    0.08
    /response
    0.07
    enor
    0.07
    TING
    0.07
    /input
    0.07
    Activations Density 0.048%

    No Known Activations