© 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. 50054
    Prev
    Next
    INDEX
    Explanations

    line representations

    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
    åŃ¦å¹´åº¦
    -0.06
    chr
    -0.06
    ä¸į以
    -0.06
    ä¸įæ²»
    -0.06
    å½ĵæľŁ
    -0.06
    çıŃåŃIJæĪIJåijĺ
    -0.06
    ä¸įåıĬ
    -0.06
    æľ«å¹´
    -0.06
    好äºĭ
    -0.06
    สà¹Īà¸ĩ
    -0.06
    POSITIVE LOGITS
    åĽ¾çļĦ
    0.08
    å¤ĦçļĦ
    0.08
    åĽĽå¤Ħ
    0.08
     choke
    0.08
    ilih
    0.08
    å¿ĹæĪIJ
    0.08
    æ´»
    0.08
    åĽ¾ä¸ŃçļĦ
    0.08
    igne
    0.07
    鼨èĬ±
    0.07
    Activations Density 0.051%

    No Known Activations