© 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. 62119
    Prev
    Next
    INDEX
    Explanations

    SQL keywords and code snippets

    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
     ("/
    -0.09
     "***
    -0.09
     //.
    -0.09
     “âĢ¦
    -0.08
     ("\
    -0.08
     ("-
    -0.07
     "...
    -0.07
    ="--
    -0.07
     _(
    -0.07
    Latch
    -0.07
    POSITIVE LOGITS
     \'
    0.12
    ..."
    0.11
     \""
    0.11
    \"
    0.11
     (âĢ¦)
    0.11
    \n
    0.11
    ‘
    0.10
     \"
    0.10
     \`
    0.10
    \""
    0.10
    Activations Density 0.524%

    No Known Activations