© 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. 22-TRANSCODER-HP
    7. 97932
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cruc
    -0.26
    çļĦå°±æĺ¯
    -0.26
     binary
    -0.26
    oretical
    -0.25
    iflower
    -0.25
     land
    -0.24
     window
    -0.24
     strip
    -0.24
     proper
    -0.24
     stir
    -0.24
    POSITIVE LOGITS
    edList
    0.29
    Setup
    0.27
    é¥
    0.26
    maker
    0.26
    Ticker
    0.25
    aN
    0.25
    ukt
    0.24
    *L
    0.24
    SDK
    0.24
    [cnt
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.