© 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. 60897
    Prev
    Next
    INDEX
    Explanations

    lambda expression, apply, sorting, callback

    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
    ¤
    -0.07
    èŀį
    -0.07
    ÐIJС
    -0.06
     Liberation
    -0.06
    å°ıæľī
    -0.06
    èŀįéĢļ
    -0.06
    /nginx
    -0.06
    unto
    -0.06
     plat
    -0.06
     accred
    -0.06
    POSITIVE LOGITS
    (lambda
    0.09
    .callback
    0.08
     onResponse
    0.08
    ayar
    0.08
     Hoc
    0.08
    ÑĢоÑı
    0.07
    út
    0.07
     callback
    0.07
     Callback
    0.07
    Expression
    0.07
    Activations Density 0.200%

    No Known Activations