© 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. 31996
    Prev
    Next
    INDEX
    Explanations

    carcinoid tumor, synaptic vesicle, restaurant scene, sex offender, psyllium husk

    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
    ÑĢоб
    -0.07
    æĽ¼
    -0.07
    åĩ¿
    -0.07
    pira
    -0.07
    éļ¨
    -0.07
    çĪĨ
    -0.07
    راÙĨ
    -0.07
     {}:
    -0.07
    æİ°
    -0.07
    rams
    -0.07
    POSITIVE LOGITS
     aka
    0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
    åĺ¹
    0.07
    åıĪ称为
    0.07
    aka
    0.07
    ä¹Łè¢«ç§°ä¸º
    0.07
    ä¹Łç§°ä¸º
    0.07
     ανά
    0.07
    íķĺìĺĢìľ¼ë©°
    0.07
    æŁ¥çľĭåħ¨éĥ¨
    0.07
    Activations Density 0.003%

    No Known Activations