© 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. 22098
    Prev
    Next
    INDEX
    Explanations

    requirement specification

    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
    大åİĤ
    -0.06
     Circ
    -0.06
    骨èĤī
    -0.06
    iná
    -0.06
    ä¸įè¿ľ
    -0.06
    å¥ı
    -0.06
    顺
    -0.05
     ÐŁÐ¾Ð»Ð¾
    -0.05
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    -0.05
    Ùĥب
    -0.05
    POSITIVE LOGITS
    åķ¼
    0.06
    uis
    0.05
     burge
    0.05
    вÑĸв
    0.05
    æ¿Ģåħī
    0.05
    hm
    0.05
    æºIJ
    0.05
    rec
    0.05
    hn
    0.05
    æķ´çIJĨ
    0.05
    Activations Density 0.006%

    No Known Activations