© 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. 141528
    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
    fos
    -0.29
    ])[
    -0.25
    çĸı
    -0.24
     @[
    -0.24
     hang
    -0.24
    åģıåģı
    -0.24
    msp
    -0.24
    NAMESPACE
    -0.24
    <!--[
    -0.24
    cip
    -0.24
    POSITIVE LOGITS
     Surprise
    0.28
    ator
    0.27
    满æĦı
    0.26
    ichern
    0.25
    ston
    0.25
    adora
    0.25
    ê°IJ
    0.24
    俱ä¹IJ
    0.23
     affirmative
    0.23
     informat
    0.23
    Activations Density 7.197%

    No Known Activations

    This feature has no known activations.