© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26268
    Prev
    Next
    INDEX
    Explanations

    reconstruction and reconstruct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJ«éĩij
    -0.07
    顺æīĭ
    -0.07
    ExceptionHandler
    -0.07
    çģµæ´»æĢ§
    -0.07
    å¤§åĽ½
    -0.07
    flex
    -0.07
    ä¸Ģéĩij
    -0.07
    å¯Ĩæĸ¯
    -0.06
    å¤ĦçIJĨæĸ¹å¼ı
    -0.06
    à¸Ĥว
    -0.06
    POSITIVE LOGITS
     reconstruction
    0.19
     reconstruct
    0.19
     Reconstruction
    0.17
     reconstructed
    0.17
    éĩį建
    0.16
     ricostr
    0.13
    è¿ĺåİŁ
    0.13
     ÑĢекон
    0.13
    å¤įåİŁ
    0.12
    éĩįæŀĦ
    0.12
    Activations Density 0.063%

    No Known Activations