© 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. 27087
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    æĢ»æ¯Ķ
    -0.08
    ArrayType
    -0.07
     Tribut
    -0.07
    forward
    -0.06
    리ì§Ģ
    -0.06
    ä¸įä¹±
    -0.06
    éĺµéĺµ
    -0.06
    æ¯Ľ
    -0.06
    æļ´
    -0.06
    åĿIJ
    -0.06
    POSITIVE LOGITS
    奶çĪ¸
    0.08
    éĨį
    0.07
    èIJ½éŃĦ
    0.07
    ssp
    0.07
    orda
    0.07
    rax
    0.07
    å·´å·´
    0.07
    öv
    0.07
     ës
    0.07
    è¿Ļé¢Ĺ
    0.06
    Activations Density 0.354%

    No Known Activations