© 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. 49031
    Prev
    Next
    INDEX
    Explanations

    reticulum and membrane components

    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
    ä¸ŀ
    -0.08
    kers
    -0.07
     rough
    -0.07
     rub
    -0.07
    ä¸Ģ串
    -0.06
    ¸
    -0.06
     Gris
    -0.06
    Installer
    -0.06
    竹
    -0.06
    cerin
    -0.06
    POSITIVE LOGITS
    åijij
    0.08
    å»»
    0.08
    ä½ľæĪIJ
    0.08
    Õ¡Õ¾
    0.08
     compart
    0.08
     INNER
    0.07
    forming
    0.07
    iep
    0.07
    غط
    0.07
    .docker
    0.07
    Activations Density 0.015%

    No Known Activations