© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14687
    Prev
    Next
    INDEX
    Explanations

    prison, inmates, confinement

    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
    ÏĨη
    -0.08
    éģºçĶ£
    -0.07
     Realt
    -0.07
    主å§Ķ
    -0.07
    ter
    -0.07
    翼翼
    -0.07
    家åºŃåĮ»çĶŁ
    -0.07
     ÑĥÑĢа
    -0.07
     panne
    -0.07
    teras
    -0.07
    POSITIVE LOGITS
     confinement
    0.14
     prisoner
    0.12
    æĭĺçķĻ
    0.12
     prison
    0.12
     inmates
    0.12
    åĽļ
    0.12
     Prison
    0.12
    ç¾ģæĬ¼
    0.11
     prisoners
    0.11
     inmate
    0.11
    Activations Density 0.277%

    No Known Activations