© 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. 14625
    Prev
    Next
    INDEX
    Explanations

    cell differentiation

    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
    utex
    -0.07
    ãģªãģı
    -0.07
    дей
    -0.07
    annies
    -0.07
    anser
    -0.06
    åĴĮåīį
    -0.06
    èĩªçĦ¶èµĦæºIJåĴĮ
    -0.06
    èļ£
    -0.06
    ombine
    -0.06
    iam
    -0.06
    POSITIVE LOGITS
    çļĦéĤ£ä¸ĢåĪ»
    0.07
    åĴĮè¡Į为
    0.07
    JNI
    0.07
    dup
    0.07
    âĢij
    0.07
    TypeEnum
    0.06
     Corso
    0.06
     transfer
    0.06
     conversion
    0.06
    管çIJĨçŃī
    0.06
    Activations Density 0.870%

    No Known Activations