© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 35036
    Prev
    Next
    INDEX
    Explanations

    YAML and configurations

    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
    Negative Logits
    aren
    -0.07
    -
    -0.06
    èļ
    -0.06
    ↵
    -0.06
    æĿı
    -0.06
    anger
    -0.06
    æijĩ
    -0.06
    åĪĴ
    -0.05
    æľīä½Ļ
    -0.05
    壹
    -0.05
    POSITIVE LOGITS
    éĴī
    0.11
    ä¸įæĹ©
    0.10
    .jupiter
    0.09
    leos
    0.09
    /filepath
    0.09
    æł¹æį®åħ¬åı¸
    0.08
    çļĦå®īæİĴ
    0.08
    _DATABASE
    0.08
    ãm
    0.08
    blok
    0.08
    Activations Density 0.001%

    No Known Activations