© 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. 20057
    Prev
    Next
    INDEX
    Explanations

    twin-twin transfusion

    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
    æī¿
    -0.08
    chado
    -0.08
    é©»
    -0.08
     Expos
    -0.07
    SX
    -0.07
     exposures
    -0.07
    客
    -0.07
    ILI
    -0.07
    enton
    -0.07
    鼰
    -0.07
    POSITIVE LOGITS
     connected
    0.09
     Connected
    0.08
    æ»ijè½®
    0.08
     masses
    0.08
    pul
    0.08
    _connected
    0.08
    æĭīåĬ¨
    0.08
    connected
    0.08
     gravitational
    0.07
    Connected
    0.07
    Activations Density 0.003%

    No Known Activations