© 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. 22196
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
    ume
    -0.06
    lez
    -0.05
    lett
    -0.05
    erd
    -0.05
    ÑĦин
    -0.05
    insky
    -0.05
    artal
    -0.05
    Ñĥк
    -0.05
    ablish
    -0.05
    è²¢çį»
    -0.05
    POSITIVE LOGITS
    éĺģ
    0.06
    é«ĺç§ij
    0.05
    åı®
    0.05
     ØŃاÙĦÛĮ
    0.05
    .apps
    0.05
     fwrite
    0.05
    жил
    0.05
    ovies
    0.05
    imal
    0.05
    é»Ħ
    0.05
    Activations Density 0.385%

    No Known Activations