© 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. 3280
    Prev
    Next
    INDEX
    Explanations

    CocoaTouch

    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
    åľĺ
    -0.07
    åı¯æ»¡è¶³
    -0.07
    ä½ĻçĥŃ
    -0.07
    atoon
    -0.07
    ÑĢиз
    -0.07
     peggi
    -0.07
    ãĤĬè¿Ķ
    -0.07
    ÑĢова
    -0.06
    ãĥ£
    -0.06
    odelist
    -0.06
    POSITIVE LOGITS
    åįĵ
    0.07
    çĽ¸çº¦
    0.07
    çļĦä¼Łå¤§
    0.06
     famously
    0.06
    ç²¾å¯Ĩ
    0.06
    มหา
    0.06
    æŃĩ
    0.06
    è¿Ļæĺ¯å¯¹
    0.06
    Ń
    0.06
    uch
    0.06
    Activations Density 0.023%

    No Known Activations