© 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. 20578
    Prev
    Next
    INDEX
    Explanations

    interrelated, overlapping, interact

    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
    åıĮæĸ¹åľ¨
    -0.09
    èŀ
    -0.08
    驹
    -0.08
    æŀĹæŀ«
    -0.08
    ÙĪار
    -0.08
    assar
    -0.08
     ÙĨص
    -0.07
    ä¸¤åľ°
    -0.07
    åı¦ä¸Ģæĸ¹
    -0.07
    ingga
    -0.07
    POSITIVE LOGITS
    缸è¾ħ
    0.09
    缸äºĴéħįåIJĪ
    0.08
     synerg
    0.08
     übersch
    0.08
    äºĴ
    0.08
     together
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    èģĶåĬ¨
    0.07
    缸äºĴ
    0.07
     взаимоÑģ
    0.07
    Activations Density 0.053%

    No Known Activations