© 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. 129924
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ighter
    -0.28
    ÑĢож
    -0.26
     births
    -0.26
    ible
    -0.25
    comp
    -0.25
    ibly
    -0.25
    ´Ģ
    -0.25
     uniform
    -0.25
    ={({
    -0.25
    æľīæĦıä¹ī
    -0.25
    POSITIVE LOGITS
    æ¶Ĥ
    0.27
    alc
    0.27
    NL
    0.25
    reib
    0.25
    uan
    0.23
    .apple
    0.23
    俺
    0.23
    å¾Īæĺ¯
    0.23
    è¿Ļä¹Ī
    0.23
    ajo
    0.23
    Activations Density 1.709%

    No Known Activations

    This feature has no known activations.