© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18034
    Prev
    Next
    INDEX
    Explanations

    sports teams, companies, and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¡·
    -0.06
    å¾·æĸ¯
    -0.06
    راÙħ
    -0.06
    Interested
    -0.06
    æĥ³åĥı
    -0.06
    eson
    -0.06
    ä¸įç»Ŀ
    -0.05
    úst
    -0.05
     دÙĦ
    -0.05
     disposition
    -0.05
    POSITIVE LOGITS
    æıIJéĺ²
    0.06
    æıIJ
    0.06
    ehl
    0.05
    veli
    0.05
     flagged
    0.05
     Ùħعرض
    0.05
    Ø·ÙĨ
    0.05
    Fo
    0.05
    hone
    0.05
     laks
    0.05
    Activations Density 0.035%

    No Known Activations