© 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. 1091
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    iform
    -0.08
    .TryParse
    -0.08
    onde
    -0.07
    ç»Ħç»ĩåįıè°ĥ
    -0.07
    parsed
    -0.07
    Ĺ
    -0.07
    åĦŁ
    -0.07
     ÙĪاÙĦÙĦÙĩ
    -0.07
    à¸Ĥัà¸Ļ
    -0.07
     Ejem
    -0.07
    POSITIVE LOGITS
    stadt
    0.09
    æĻ´
    0.07
    aku
    0.07
    ãĤ¹ãĥĪãĥ¬
    0.07
    artal
    0.07
    æľīå¾ħ
    0.07
    strup
    0.07
    requencies
    0.06
     пон
    0.06
    éļ¾æ±Ĥ
    0.06
    Activations Density 0.000%

    No Known Activations