© 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. 50119
    Prev
    Next
    INDEX
    Explanations

    class assignment, method calling

    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
    æĤį
    -0.07
    orning
    -0.07
     rede
    -0.07
    æŃ£éĿ¢çļĦ
    -0.07
    åģ¥åħ¨
    -0.06
    gra
    -0.06
    rad
    -0.06
    εÏģ
    -0.06
    .verify
    -0.06
    ibal
    -0.06
    POSITIVE LOGITS
    åĪĨéļĶ
    0.11
     continuity
    0.10
    chow
    0.09
    åĪĨåī²
    0.09
    Separator
    0.09
    è¿ŀç»ŃæĢ§
    0.09
     непÑĢеÑĢÑĭв
    0.08
     continuidad
    0.08
     separators
    0.08
    -break
    0.08
    Activations Density 0.027%

    No Known Activations