© 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. 31719
    Prev
    Next
    INDEX
    Explanations

    electronic systems and appliances

    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
    arity
    -0.08
    è¿ĺæĺ¯ä¸Ģ个
    -0.08
     mancan
    -0.08
    borgen
    -0.08
    âu
    -0.08
    ùi
    -0.07
    åıĤä¼ļ
    -0.07
    æĸĩæĺİå®ŀè·µ
    -0.07
    adero
    -0.07
    blas
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
    彤
    0.07
     sonstige
    0.07
    urz
    0.06
     goods
    0.06
    æĪĸæľįåĬ¡
    0.06
    apons
    0.06
    iany
    0.06
    ihe
    0.06
    æĴĴ
    0.06
    Activations Density 0.230%

    No Known Activations