© 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. 29457
    Prev
    Next
    INDEX
    Explanations

    code delimiters or mathematical variables

    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
    ali
    -0.07
    деб
    -0.07
    ä¸įä¼ļ
    -0.06
    å¼ģ
    -0.06
    ijn
    -0.06
    йда
    -0.06
     suff
    -0.06
     Deb
    -0.06
    ä¸įèĥľæķ°
    -0.06
    ×Ļ×Ļ
    -0.06
    POSITIVE LOGITS
     appunto
    0.08
    ymes
    0.08
    æľŁæ»¡åIJİ
    0.07
    åĽŀçŃĶéĩı
    0.07
     div
    0.07
    tones
    0.07
    «
    0.07
    anguages
    0.07
    çĻ½çİī
    0.07
    athom
    0.07
    Activations Density 0.001%

    No Known Activations