© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107826
    Prev
    Next
    INDEX
    Explanations

    medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fast
    -0.29
    æĮĩ
    -0.28
     sure
    -0.27
    è§ŀ
    -0.27
     ._
    -0.27
    å¿«
    -0.25
    年轻人
    -0.24
    çļĦ社ä¼ļ
    -0.24
    ÑĢегион
    -0.24
     negatively
    -0.23
    POSITIVE LOGITS
    год
    0.30
    æĪIJåĬŁçļĦ
    0.27
    nee
    0.25
    arem
    0.25
    åݻ年
    0.25
     Weg
    0.25
     Wa
    0.24
    ä¸įèµ·
    0.24
     heter
    0.24
     Naj
    0.24
    Activations Density 9.165%

    No Known Activations