© 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. 21995
    Prev
    Next
    INDEX
    Explanations

    making code for programs and classes

    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
    awal
    -0.07
    è¸Ĭ
    -0.06
    第ä¸ĢæĿ¡
    -0.06
    ä¸Ĭä»»
    -0.06
    chner
    -0.06
    åį±æĢ¥
    -0.06
    ä»Ĭå¤ľ
    -0.06
    ä¹ĭæĢ¥
    -0.06
    æŀľãģŁ
    -0.06
    ä»»ä¸Ģ
    -0.05
    POSITIVE LOGITS
    eld
    0.07
    äºĪ
    0.06
    _try
    0.06
    æł¼åŃIJ
    0.05
    ä¸įåħ¨
    0.05
    åģļå·¥
    0.05
    á»įt
    0.05
    ulk
    0.05
    ä¸įæĺĵ
    0.05
    åıijåĬ¨
    0.05
    Activations Density 0.005%

    No Known Activations