© 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. 50236
    Prev
    Next
    INDEX
    Explanations

    movement and displacement

    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
    æºIJæºIJ
    -0.08
    anian
    -0.07
    isos
    -0.07
    èĴ¸èĴ¸æĹ¥ä¸Ĭ
    -0.07
    ä¼´ä½ł
    -0.07
    _recursive
    -0.07
    ä»ĺ
    -0.07
    ehn
    -0.07
     collapsing
    -0.07
     declining
    -0.07
    POSITIVE LOGITS
    移åĬ¨
    0.08
    æĸ¹åIJijåĴĮ
    0.08
    ä¸įå½Ĵ
    0.08
     away
    0.08
    ä½į移
    0.08
    acement
    0.08
    çĽ¸å¯¹äºİ
    0.08
    å¹ħ度
    0.08
    æĸ¹åIJijçļĦ
    0.08
     movements
    0.08
    Activations Density 0.059%

    No Known Activations