© 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. 11113
    Prev
    Next
    INDEX
    Explanations

    `Inc`

    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
    ç½ij讯
    -0.08
    Ĺı
    -0.07
    çļĦä¸ĵæłı
    -0.07
     ÏĥÏħνο
    -0.07
    åįĬåľº
    -0.07
    iswa
    -0.07
    èı²å°Ķå¾·
    -0.07
    绿油
    -0.07
    вÑĮÑİ
    -0.07
    tower
    -0.07
    POSITIVE LOGITS
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    ge
    0.06
    oker
    0.06
    лон
    0.06
     fur
    0.05
    áz
    0.05
    å¼ķ
    0.05
    ="__
    0.05
    åłª
    0.05
    esseract
    0.05
    Activations Density 0.132%

    No Known Activations