© 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. 63269
    Prev
    Next
    INDEX
    Explanations

    egg or eggs

    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
    rug
    -0.08
    æłijæľ¨
    -0.08
    gespr
    -0.07
    ÙĦÙĪÙĦ
    -0.07
    eria
    -0.07
    erland
    -0.07
    ¬ģ
    -0.07
    çĬ¬
    -0.07
    Interpolator
    -0.07
    ìĤ¬íķŃ
    -0.07
    POSITIVE LOGITS
     eggs
    0.10
    åѵ
    0.09
    å·£
    0.09
    é¸ŃèĽĭ
    0.09
    èĽĭ
    0.09
    åѵåĮĸ
    0.09
    åįµ
    0.08
     hatch
    0.08
     egg
    0.08
    egg
    0.08
    Activations Density 0.030%

    No Known Activations