© 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. 14872
    Prev
    Next
    INDEX
    Explanations

    "A:" / "that" / "actually" followed by sentence context

    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
    illage
    -0.06
    pek
    -0.06
    ered
    -0.06
    ä»Ģ
    -0.06
    çĽĬ
    -0.06
    ç¦»åľº
    -0.06
    æĹ¥æĹ¥
    -0.06
    oot
    -0.06
    ä½ķå¿ħ
    -0.06
    point
    -0.06
    POSITIVE LOGITS
    agam
    0.08
    æĬŀ
    0.08
    agu
    0.08
    здÑĢа
    0.08
     />'
    0.08
    æľīåħ³äººåijĺ
    0.08
     "<?
    0.07
    .vert
    0.07
     Ùħزد
    0.07
    å¾ĹæĿ¥
    0.07
    Activations Density 0.001%

    No Known Activations