© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1384
    Prev
    Next
    INDEX
    Explanations

    enabling improvement or reduction

    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
    enaar
    -0.08
    åĽłä¸ºæľīäºĨ
    -0.08
    ãģĿãģĨãģ§ãģĻãģĮ
    -0.07
    ä¼ģä¸ļæ³ķ人
    -0.07
    ãģ®ãģĬãģĭãģĴ
    -0.07
     due
    -0.07
    天ä»Ļ
    -0.07
    Č
    -0.07
    berger
    -0.07
    pees
    -0.07
    POSITIVE LOGITS
    æĽ´å®¹æĺĵ
    0.09
     wiederum
    0.08
     overall
    0.08
    æķ´ä½ĵ
    0.08
    æĽ´æĺĵ
    0.07
    èĤ¯
    0.07
     further
    0.07
     Overall
    0.07
    æķ´ä½ĵä¸Ĭ
    0.07
    èIJĮ
    0.07
    Activations Density 0.108%

    No Known Activations