© 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. 51572
    Prev
    Next
    INDEX
    Explanations

    CSS selectors or HTML tags

    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
     "***
    -0.08
    olla
    -0.08
    atori
    -0.08
    rou
    -0.07
    éľ²
    -0.07
    رØŃ
    -0.07
    æļ´éľ²
    -0.06
    à¤Ĥà¤Ł
    -0.06
    imps
    -0.06
    uela
    -0.06
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.09
    äºĮåŃĹ
    0.09
    âĹĭâĹĭ
    0.08
    è¿Ļ个è¯į
    0.07
     XXI
    0.07
     rather
    0.07
    ä¸Ģè¯į
    0.07
    ismus
    0.07
     refers
    0.07
     plutôt
    0.07
    Activations Density 0.004%

    No Known Activations