© 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. 19763
    Prev
    Next
    INDEX
    Explanations

    headphones and headsets

    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
    ä¸īéŨ
    -0.06
    满
    -0.06
    åľŁåľ°ä¸Ĭ
    -0.06
     scare
    -0.06
    æ½¢
    -0.06
    çĩİ
    -0.05
    è¿Ľç¨ĭçļĦ
    -0.05
     endanger
    -0.05
     catal
    -0.05
    æĹº
    -0.05
    POSITIVE LOGITS
     headphones
    0.07
     наÑĥÑĪ
    0.07
    èĢ³æ©Ł
    0.06
    èĢ³æľº
    0.06
    yty
    0.06
    éģĵè¿ľ
    0.06
     headphone
    0.06
    หู
    0.06
    éĻįåĻª
    0.06
    иÑĤай
    0.06
    Activations Density 0.012%

    No Known Activations