© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26990
    Prev
    Next
    INDEX
    Explanations

    translation sequence

    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
    ��
    -0.09
    �
    -0.07
    Ãĥ
    -0.07
    "."
    -0.07
    ï¸ı
    -0.07
    çĤ¹åĩ»ä¸ĭè½½
    -0.07
    ���
    -0.07
    "..
    -0.06
     nbytes
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    éĥ½æĺ¯åı¯ä»¥
    0.08
    oka
    0.07
    ÑĢиз
    0.07
    anei
    0.07
    ä¹Łæĺ¯è¦ģ
    0.07
    ä¹Łæĺ¯åı¯ä»¥
    0.07
    å¯¹æľ¬æ¬¡
    0.07
    åIJĮä¸Ĭ
    0.07
    iativa
    0.07
    ennes
    0.07
    Activations Density 0.036%

    No Known Activations