© 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. 2485
    Prev
    Next
    INDEX
    Explanations

    CSS border-radius and button styling

    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
    éĴ©
    -0.08
    umer
    -0.08
     Hook
    -0.07
    ÙĬس
    -0.07
     fine
    -0.07
     hook
    -0.07
    çĶ»çļĦ
    -0.07
    å±Ģéķ¿
    -0.06
     unseen
    -0.06
     unrestricted
    -0.06
    POSITIVE LOGITS
    è¾¹æ¡Ĩ
    0.08
     rounded
    0.08
     border
    0.08
    -border
    0.08
    ToDevice
    0.08
    rounded
    0.07
    duration
    0.07
     borderRadius
    0.07
    Border
    0.07
    hape
    0.07
    Activations Density 0.095%

    No Known Activations