© 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. 49408
    Prev
    Next
    INDEX
    Explanations

    code comparison operators

    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
    èĢħä¹Ł
    -0.08
    à¸ģà¹ĩà¹Ħà¸Ķà¹ī
    -0.08
    éĿŀ常好
    -0.07
    æĥļ
    -0.07
    éĺĸ家
    -0.07
    ä¸įäºĨå¤ļä¹ħ
    -0.07
    )<<
    -0.07
    è®¤çľŁè´¯å½»
    -0.07
     (;;
    -0.07
    èį¸
    -0.07
    POSITIVE LOGITS
     ==
    0.09
     Formular
    0.08
     !=
    0.07
    oupon
    0.07
    visor
    0.07
     ÑħоÑĤÑĮ
    0.07
    æľīä»»ä½ķ
    0.07
    æŃ£å¥½
    0.07
    sse
    0.07
    _LOGGER
    0.06
    Activations Density 0.029%

    No Known Activations