© 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. 62994
    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
    nü
    -0.28
    eled
    -0.26
    {})↵
    -0.25
    åħ·ä½ĵåĨħ容
    -0.25
    åĬĽè¿ĺæĺ¯
    -0.25
    (ff
    -0.25
    ysize
    -0.25
    {})
    -0.25
    )[:
    -0.24
     bluff
    -0.24
    POSITIVE LOGITS
     fabricated
    0.27
    ii
    0.27
     min
    0.27
     Foundation
    0.27
     thin
    0.27
    ender
    0.26
     Def
    0.26
     fabric
    0.26
     Fabric
    0.26
    èĸĦ
    0.26
    Activations Density 48.195%

    No Known Activations

    This feature has no known activations.