© 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. 18075
    Prev
    Next
    INDEX
    Explanations

    live streams and chat

    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
    compact
    -0.06
    CSI
    -0.06
    oss
    -0.06
    æ²¹èıľ
    -0.05
    æĸĩä»¶æł¼å¼ı
    -0.05
    bul
    -0.05
    å§Ĺ
    -0.05
    unny
    -0.05
     compact
    -0.05
    åħ¶éĹ´
    -0.05
    POSITIVE LOGITS
    æµģ
    0.07
    缴æĴŃ
    0.06
    ç¹į
    0.06
     volatile
    0.06
     livest
    0.05
     аппаÑĢаÑĤ
    0.05
    çĽ¯çĿĢ
    0.05
     streams
    0.05
    Live
    0.05
     live
    0.05
    Activations Density 0.016%

    No Known Activations