© 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. 57426
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     inconvenience
    -0.08
    enner
    -0.07
    éĢļ天
    -0.07
    åį«
    -0.07
    หà¸Ļ
    -0.07
    TEX
    -0.07
    åĽŀãĤĬ
    -0.07
    eled
    -0.07
     ConfigurationManager
    -0.07
    ibi
    -0.07
    POSITIVE LOGITS
    tern
    0.07
    å§Ķåijĺ
    0.07
    èıľ
    0.07
    åŁ¼
    0.07
    ["$
    0.07
    èĴ¸èĴ¸
    0.06
     أبر
    0.06
     ÑĢеÑĦлек
    0.06
    ichen
    0.06
    蹦
    0.06
    Activations Density 0.000%

    No Known Activations