© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12746
    Prev
    Next
    INDEX
    Explanations

    environmental factors and influences

    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
    çĮĽè¿Ľ
    -0.09
    cing
    -0.08
    itive
    -0.08
    ë§ĪìŀIJ
    -0.08
    ãģ£ãģĵãģĨ
    -0.07
     Setia
    -0.07
    ковод
    -0.07
    ámara
    -0.07
    åĪ©äºļ
    -0.07
    çīĩæľº
    -0.07
    POSITIVE LOGITS
    IRONMENT
    0.14
    füg
    0.09
    à¸Ļà¹Į
    0.08
    psilon
    0.08
    alf
    0.08
    -wide
    0.08
    .getExternalStorage
    0.08
    tä
    0.08
    ļ
    0.08
    ually
    0.08
    Activations Density 0.043%

    No Known Activations