© 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. 23766
    Prev
    Next
    INDEX
    Explanations

    ; followed by web

    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
    insa
    -0.08
    \"\
    -0.08
    qui
    -0.08
    <?>
    -0.08
    çe
    -0.08
    zeitig
    -0.08
    åĽłä¸ºè¿ĻäºĽ
    -0.08
     Ãļl
    -0.07
    ets
    -0.07
    OW
    -0.07
    POSITIVE LOGITS
    0.17
    Ù°
    0.08
     ((!
    0.08
     (!((
    0.07
    ï¸ı
    0.07
    Ìģ
    0.07
     (![
    0.07
     ,
    0.07
    Ñĥж
    0.07
    åĦ¿çļĦ
    0.07
    Activations Density 0.009%

    No Known Activations