© 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. 141671
    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
    èļĤ
    -0.27
    une
    -0.27
    mesh
    -0.26
    yl
    -0.25
    fills
    -0.24
    ane
    -0.24
    unate
    -0.24
    æĶ¾å¿ĥ
    -0.24
    åĩ¡
    -0.23
    ä¹ĺåĿIJ
    -0.23
    POSITIVE LOGITS
    омеÑĢ
    0.26
    ÑĨиалÑĮно
    0.25
    .fm
    0.25
    rico
    0.25
    .lu
    0.25
    ç¼Ĺ
    0.24
    å¾Ĺ好
    0.24
    ecom
    0.24
    毯
    0.24
    BOARD
    0.24
    Activations Density 45.066%

    No Known Activations

    This feature has no known activations.