© 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. 45817
    Prev
    Next
    INDEX
    Explanations

    match/mismatch comparison

    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
    é»ĺ
    -0.06
    åı¶
    -0.06
    åĿĤ
    -0.06
    ignon
    -0.06
    ublic
    -0.06
    leton
    -0.06
     eman
    -0.06
    .norm
    -0.06
    alter
    -0.06
    æĹłè¨Ģ
    -0.06
    POSITIVE LOGITS
    åĮ¹éħį
    0.13
    åĮ¹éħįçļĦ
    0.13
    Mismatch
    0.12
     mismatch
    0.12
     match
    0.11
     Matches
    0.11
     matched
    0.11
     Match
    0.11
     matches
    0.11
     matching
    0.11
    Activations Density 0.135%

    No Known Activations