© 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. 17363
    Prev
    Next
    INDEX
    Explanations

    code blocks and keywords

    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
    PTH
    -0.07
    arat
    -0.06
     вдÑĢÑĥг
    -0.06
    kow
    -0.06
    亨
    -0.06
    à¸Ĺาà¸ĩ
    -0.06
    kest
    -0.06
    utul
    -0.06
    家ä¼Ļ
    -0.06
    rong
    -0.05
    POSITIVE LOGITS
    æĸ
    0.06
    è¿ĺæĺ¯åı¯ä»¥
    0.06
    al
    0.05
    ç£ĭ
    0.05
    E
    0.05
    çļĦå°±æĺ¯
    0.05
    ter
    0.05
    ÅĦ
    0.05
    åģļçļĦå°±æĺ¯
    0.05
    æĺ§
    0.05
    Activations Density 0.007%

    No Known Activations