© 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. 21144
    Prev
    Next
    INDEX
    Explanations

    medical treatments or conditions

    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
    cer
    -0.06
    çĶ¨æĿ¥
    -0.06
    å¡
    -0.06
    鸦
    -0.06
    anza
    -0.06
    kens
    -0.06
    åıĹ
    -0.06
    éĨ
    -0.06
    缴æİ¥åľ¨
    -0.06
    ais
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩ以ä¸Ĭ
    0.10
    ãģĦãģĭãģĮ
    0.09
    åħ¨éĿ¢äºĨ解
    0.09
    以ä¸Ĭå°±æĺ¯
    0.09
    以ä¸Ĭæĺ¯
    0.09
    “These
    0.08
    quilib
    0.08
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.08
    éĢļè¿ĩè¿ĻäºĽ
    0.08
    大åıĺ
    0.07
    Activations Density 0.003%

    No Known Activations