© 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. 2564
    Prev
    Next
    INDEX
    Explanations

    mathematical expression or formula

    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
    ernal
    -0.09
    slots
    -0.08
    ä¾ĽåºĶä¿¡æģ¯
    -0.08
    ensif
    -0.07
    è¿Ļ群
    -0.07
    å¾Ĺ天çĭ¬
    -0.07
    otos
    -0.07
    uxe
    -0.07
    å®ŀç¼´
    -0.07
    endale
    -0.07
    POSITIVE LOGITS
     formula
    0.09
     compound
    0.09
     expression
    0.08
    åħ¬å¼ı
    0.08
     inequality
    0.08
     formule
    0.07
     formul
    0.07
     equation
    0.07
    auan
    0.07
     ÑĦоÑĢмÑĥ
    0.07
    Activations Density 0.007%

    No Known Activations