© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13984
    Prev
    Next
    INDEX
    Explanations

    code includes

    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
    Õ®
    -0.08
     @}
    -0.08
    ä¸ĭæīĭ
    -0.07
    è¦ģé¢Ĩ
    -0.07
    visa
    -0.07
    ä¸Ģç»ı
    -0.07
    Wr
    -0.07
    Regards
    -0.06
    åĨįè¿ĩ
    -0.06
    Ùĩب
    -0.06
    POSITIVE LOGITS
    æī¿
    0.07
    rael
    0.07
    åĴĮåŁ¹åħ»
    0.07
    å¾·éĺ³
    0.07
    å¼Ģè¾Ł
    0.07
    åĸĥ
    0.07
    κÏĦή
    0.06
    зан
    0.06
    ãģĭãģŃ
    0.06
    ipan
    0.06
    Activations Density 0.043%

    No Known Activations