© 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. 40386
    Prev
    Next
    INDEX
    Explanations

    lung cancer patients, health data

    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
     Dout
    -0.08
    å¾ħ
    -0.08
    sville
    -0.07
    å¾ħå®ļ
    -0.07
     Programma
    -0.07
    maal
    -0.07
    åħ¶éģĵ
    -0.07
    Invoker
    -0.07
    ator
    -0.07
    ector
    -0.07
    POSITIVE LOGITS
    æľīäºĭ
    0.07
    ãģķãģ¾
    0.07
    ith
    0.07
    èĥ±
    0.07
    ihan
    0.07
    _ACCEPT
    0.07
    漪
    0.07
    zgl
    0.07
    jong
    0.07
    è»Ĵ
    0.07
    Activations Density 0.198%

    No Known Activations