© 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. 130622
    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
     moment
    -0.28
    setLabel
    -0.28
    MMC
    -0.27
     fencing
    -0.27
    ļĮ
    -0.27
     MOM
    -0.26
    tridge
    -0.26
     borderColor
    -0.25
    empo
    -0.25
    istical
    -0.25
    POSITIVE LOGITS
    ffect
    0.26
    -case
    0.25
     haunt
    0.25
    ikk
    0.25
     ARGS
    0.25
    ËĮ
    0.24
    avy
    0.24
    æijĺè¦ģ
    0.24
    gebra
    0.23
     hel
    0.23
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.