© 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. 9945
    Prev
    Next
    INDEX
    Explanations

    wrapping functions in closures

    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
    åĨį说äºĨ
    -0.07
    TEX
    -0.06
    éĹ»
    -0.06
     tumble
    -0.06
    hear
    -0.06
     ruled
    -0.06
    èĻŀ
    -0.06
    lag
    -0.06
     starred
    -0.06
    æ¦
    -0.06
    POSITIVE LOGITS
    Reusable
    0.10
     callable
    0.09
    callable
    0.09
     arity
    0.08
    wrap
    0.08
     functional
    0.08
    æŀĦéĢłåĩ½æķ°
    0.08
    .wrap
    0.08
    æĶ¹éĢł
    0.08
     wrap
    0.08
    Activations Density 0.143%

    No Known Activations