© 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. 18161
    Prev
    Next
    INDEX
    Explanations

    using System;

    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
    bers
    -0.06
     оÑĤÑģе
    -0.06
    ì§ĵ
    -0.05
    .Append
    -0.05
    èĦĵ
    -0.05
    éľŀ
    -0.05
    æĮł
    -0.05
    èĶ½
    -0.05
    ç®ķ
    -0.05
     sis
    -0.05
    POSITIVE LOGITS
    าà¸ģล
    0.06
    åİ¥
    0.06
    екÑģи
    0.05
     adaptive
    0.05
    被åĪ«äºº
    0.05
    allee
    0.05
    minster
    0.05
    yec
    0.05
    æ´ĭ
    0.05
    ,message
    0.05
    Activations Density 0.043%

    No Known Activations