© 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. 64125
    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
    -Cs
    -0.28
     Introduced
    -0.26
    uxt
    -0.25
    &S
    -0.25
    ventus
    -0.25
    ORY
    -0.25
     ($)
    -0.25
    å§ĭ
    -0.24
    -China
    -0.24
     Investing
    -0.24
    POSITIVE LOGITS
    shelf
    0.30
     moderne
    0.24
    AGED
    0.24
     Brut
    0.24
    =back
    0.24
    notes
    0.24
     shelf
    0.24
     reasons
    0.23
     Closet
    0.23
    åĻ¤
    0.23
    Activations Density 3.857%

    No Known Activations

    This feature has no known activations.