© 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. 17834
    Prev
    Next
    INDEX
    Explanations

    mathematical questions and calculations

    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
    otr
    -0.06
    离ä¸įå¼Ģ
    -0.06
    å®ŀè´¨æĢ§
    -0.05
    åķĨæľº
    -0.05
    emiÅŁ
    -0.05
    ìĨ¡
    -0.05
    éļĻ
    -0.05
    ç»ıèIJ¥å¼Ĥ常
    -0.05
     ëªħ
    -0.05
    åĮĸãģĻãĤĭ
    -0.05
    POSITIVE LOGITS
    åı¯æĥ³
    0.05
    å¹
    0.05
    ç¥Ń
    0.05
    anze
    0.05
    رÙĬات
    0.05
    zie
    0.05
    _mut
    0.05
    limits
    0.05
    rylic
    0.05
    ä¾
    0.05
    Activations Density 0.273%

    No Known Activations