© 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. 17123
    Prev
    Next
    INDEX
    Explanations

    efficiency and cost

    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»ĺ款æĸ¹å¼ı
    -0.06
    ä¹į
    -0.05
    ÑĮÑİ
    -0.05
    票
    -0.05
    æĮīæľŁ
    -0.05
    åİĭåĬĽçļĦ
    -0.05
    éķĩå®ļ
    -0.05
    维稳
    -0.05
    æ°ı
    -0.05
    èļģ
    -0.05
    POSITIVE LOGITS
    æįŁèĢĹ
    0.08
     losses
    0.08
    losing
    0.07
    åĩĢåĪ©
    0.07
     efficiency
    0.06
     ineff
    0.06
    åħ¨ç¨ĭ
    0.06
     Efficiency
    0.06
    çľģéģĵ
    0.06
    ded
    0.06
    Activations Density 0.034%

    No Known Activations