© 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. 39143
    Prev
    Next
    INDEX
    Explanations

    escape characters

    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
    ela
    -0.07
    ODO
    -0.06
    åħ¼æĢ»ç»ıçIJĨ
    -0.06
    æĪĸåħ¶å®ĥ
    -0.06
    æĪĸåħ¶ä»ĸ
    -0.06
    pot
    -0.06
    sem
    -0.06
     po
    -0.05
    isto
    -0.05
    hon
    -0.05
    POSITIVE LOGITS
     appunto
    0.11
    èªī为
    0.08
    wargs
    0.08
    ×ķר×ļ
    0.08
    [href
    0.08
     famously
    0.08
    iani
    0.07
    ÙħØŃ
    0.07
    ±
    0.07
     Slash
    0.07
    Activations Density 0.031%

    No Known Activations