© 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. 40388
    Prev
    Next
    INDEX
    Explanations

    forms or combinations with "-site"

    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
    iedz
    -0.07
     throw
    -0.06
     swell
    -0.06
    éĤ®å¯Ħ
    -0.06
    å¥Ĺ
    -0.06
    é©
    -0.06
     conserv
    -0.06
    Fly
    -0.06
    èķ
    -0.06
    ç¼ħ
    -0.06
    POSITIVE LOGITS
     Sites
    0.10
     sites
    0.10
    sites
    0.09
     onto
    0.09
    Sites
    0.09
    site
    0.09
    ucia
    0.09
    -site
    0.08
    Site
    0.08
     Site
    0.08
    Activations Density 0.016%

    No Known Activations