© 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. 38332
    Prev
    Next
    INDEX
    Explanations

    redistributions of source code

    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
     undermin
    -0.07
    Č
    -0.07
    adak
    -0.07
    ä¹Łå¤§
    -0.07
    ��
    -0.07
     pronto
    -0.06
    agon
    -0.06
    èĭ¥å¹²éĹ®é¢ĺçļĦ解éĩĬ
    -0.06
    å±ķå¼Ģåħ¨æĸĩ
    -0.06
    Qed
    -0.06
    POSITIVE LOGITS
    åĩ¡æľ¬ç½ij注æĺİ
    0.10
    ä¹Łæĺ¯æľĢ
    0.09
    ³³³³
    0.09
    æĹ¢çĦ¶æĺ¯
    0.08
    ilton
    0.08
    ³³³³³³³
    0.07
    ï¸İ
    0.07
    jenigen
    0.07
    åħ³äºİ
    0.07
    ï¸ı
    0.07
    Activations Density 0.054%

    No Known Activations