© 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. 141708
    Prev
    Next
    INDEX
    Explanations

    Business and geography contexts

    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
     CONTRIBUTORS
    -0.29
    æĻĸ
    -0.26
    æĥħ
    -0.26
    eba
    -0.24
    rice
    -0.24
    kers
    -0.24
     Chip
    -0.24
    rina
    -0.24
    -pin
    -0.24
     FORMAT
    -0.23
    POSITIVE LOGITS
    PTH
    0.25
    plorer
    0.24
     fel
    0.24
    èĻ½çĦ¶æĺ¯
    0.24
    hua
    0.24
    åį³ä½¿æĺ¯
    0.24
    çķ¹
    0.24
    åIJij社ä¼ļ
    0.24
     felon
    0.23
    glomer
    0.23
    Activations Density 5.598%

    No Known Activations