© 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. 64122
    Prev
    Next
    INDEX
    Explanations

    reducing gas, washing, eventually, ultraviolet

    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
    chan
    -0.08
    天åij½
    -0.07
    ä¿Ŀè¯ģåħ¶
    -0.07
    azin
    -0.07
    æµģè¡Ģ
    -0.07
     Elements
    -0.07
    Elements
    -0.07
     Elemente
    -0.07
    ادات
    -0.07
    _regression
    -0.07
    POSITIVE LOGITS
    ä½ľçĶ¨äºİ
    0.11
     everywhere
    0.10
    对åħ¶ä»ĸ
    0.09
    对ä¸ĢäºĽ
    0.09
    å½±åĵįäºĨ
    0.08
    åĪ°å¤Ħ
    0.08
     khắp
    0.08
    ä¼ļå½±åĵį
    0.08
    çī¹åĪ«æĺ¯å¯¹
    0.08
     Everywhere
    0.08
    Activations Density 0.485%

    No Known Activations