© 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. 45604
    Prev
    Next
    INDEX
    Explanations

    list of citations or list items

    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
    -0.09
    oit
    -0.08
    <|box_end|>
    -0.07
    edula
    -0.07
    áĢ·áĢº
    -0.07
    lify
    -0.07
    enburg
    -0.07
    çİ©è¿ĩ
    -0.07
    ä¹ĭé«ĺ
    -0.07
    uai
    -0.06
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.08
    ”**.
    0.07
    ä»Ģä¹Īåij¢
    0.07
    о
    0.07
    人æĦı
    0.07
    ãģĿãģĨãģ§
    0.07
    à¸ģาร
    0.07
    ä¸Ģ个å°ı
    0.07
    annya
    0.07
    ental
    0.06
    Activations Density 0.013%

    No Known Activations