© 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. 9567
    Prev
    Next
    INDEX
    Explanations

    memory allocation and garbage collection

    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
    çĿ¦
    -0.08
    obot
    -0.08
    Bracket
    -0.08
    ç¦ģæ¯Ĵ
    -0.08
     Burg
    -0.08
     mù
    -0.07
    feeds
    -0.07
     tut
    -0.07
    çĤ®
    -0.07
    {text
    -0.07
    POSITIVE LOGITS
     Allocation
    0.09
     allocations
    0.09
     reclaim
    0.09
     allocation
    0.09
    åĽŀæĶ¶
    0.09
    åįłçĶ¨
    0.08
    allocation
    0.08
     sizes
    0.08
    åĨħåŃĺ
    0.08
     partitions
    0.08
    Activations Density 0.185%

    No Known Activations