© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20298
    Prev
    Next
    INDEX
    Explanations

    query, join, request, assessment, command

    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
    ..)
    -0.07
    æĿ¥è¡¨è¾¾
    -0.07
    untr
    -0.06
    zun
    -0.06
    æĿ¥èİ·åıĸ
    -0.06
    oland
    -0.06
    ä¿IJ
    -0.06
    maks
    -0.06
    -now
    -0.06
    undur
    -0.06
    POSITIVE LOGITS
    ned
    0.06
    weg
    0.05
    atted
    0.05
    æľĽ
    0.05
    chy
    0.05
    aul
    0.05
    ative
    0.05
     însÄĥ
    0.05
    åĽłä¸ºå¥¹
    0.05
     depending
    0.05
    Activations Density 0.059%

    No Known Activations