© 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. 57933
    Prev
    Next
    INDEX
    Explanations

    contact information and appointments

    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
    éļıçĿĢæŶéĹ´çļĦ
    -0.07
    æĪ¿äº§ç½ij
    -0.06
    çĶ¨æĪ·ä¸Ĭä¼ł
    -0.06
    æľ¬ç«ĻåĨħ容
    -0.06
    åĿĩæĿ¥èĩªäºĴèģĶç½ij
    -0.06
    ãĤĦãĤī
    -0.06
    飯åºĹ
    -0.06
    íıŃ
    -0.06
    ^K
    -0.06
    å¤ļ大çļĦ
    -0.06
    POSITIVE LOGITS
    contact
    0.09
     tel
    0.09
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.09
     адÑĢеÑģÑĥ
    0.09
    èģĶç³»çĶµè¯Ŀ
    0.09
    çĥŃ线çĶµè¯Ŀ
    0.09
     contact
    0.08
    tel
    0.08
    Tel
    0.08
     anytime
    0.08
    Activations Density 0.741%

    No Known Activations