© 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. 19713
    Prev
    Next
    INDEX
    Explanations

    code comments and special 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
    çī¹åĪ«å£°æĺİ
    -0.07
    ****************************
    -0.07
     ((*
    -0.07
    oped
    -0.07
    andre
    -0.06
    TypeID
    -0.06
    ãģĶãģ¨
    -0.06
    ><![
    -0.06
    zat
    -0.06
     permitting
    -0.06
    POSITIVE LOGITS
    èĢĮæĺ¯åĽłä¸º
    0.07
    æĥķ
    0.07
    راÙģ
    0.07
    å°Ķ夫
    0.07
    oons
    0.07
    åĤħ
    0.07
    æ´ŀ
    0.07
    ddb
    0.07
    enance
    0.07
    lect
    0.07
    Activations Density 0.010%

    No Known Activations