© 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. 21292
    Prev
    Next
    INDEX
    Explanations

    data logic and state management

    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
    å½ķå¾Ĺ
    -0.09
     instagram
    -0.08
    evas
    -0.08
    iband
    -0.08
    egna
    -0.08
    VMLINUX
    -0.08
    ebro
    -0.07
    åħ¨è¦ĨçĽĸ
    -0.07
    _decoder
    -0.07
    .ipv
    -0.07
    POSITIVE LOGITS
    æĬ½è±¡
    0.09
     data
    0.09
     logic
    0.09
     asynchronously
    0.08
     execution
    0.08
    éĢ»è¾ij
    0.08
     orchest
    0.08
     CRUD
    0.07
     abstraction
    0.07
     asynchronous
    0.07
    Activations Density 0.720%

    No Known Activations