© 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. 16156
    Prev
    Next
    INDEX
    Explanations

    fine/refine or finer/refining

    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
    witz
    -0.09
    ailles
    -0.08
    sWith
    -0.08
    ات
    -0.08
    aurus
    -0.08
    <![
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    Ø©
    -0.08
    mit
    -0.08
    é£İäºij
    -0.08
    POSITIVE LOGITS
    åħ¥å¾®
    0.11
    amental
    0.10
    erc
    0.09
    (er
    0.09
     جدÙĭا
    0.08
    ishing
    0.08
    lessly
    0.08
    à¹Ĩ
    0.08
    ighted
    0.08
    ç¨ĭ度
    0.08
    Activations Density 0.027%

    No Known Activations