© 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. 28186
    Prev
    Next
    INDEX
    Explanations

    library imports and definitions

    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
    çŃīåħ¶ä»ĸ
    -0.07
     tie
    -0.06
    upe
    -0.06
    æĮīåħ¶
    -0.06
     Stanis
    -0.06
     Singh
    -0.06
    Ùİاع
    -0.06
     pant
    -0.06
     ties
    -0.06
    illes
    -0.06
    POSITIVE LOGITS
    ä¸īä¸Ń
    0.08
    iere
    0.08
    å¸Ĥæĸ°
    0.08
    åħ¨åĬĽåģļ好
    0.07
    UNK
    0.07
     appunto
    0.07
    رÙĪت
    0.07
    ymp
    0.07
    ãģ¾ãģĦ
    0.07
    dio
    0.07
    Activations Density 0.323%

    No Known Activations