© 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. 130509
    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
    aison
    -0.29
    chest
    -0.28
     Existing
    -0.28
     &'
    -0.27
     shel
    -0.27
     Already
    -0.26
     shelf
    -0.26
     (:
    -0.25
     Shelter
    -0.25
     shelves
    -0.24
    POSITIVE LOGITS
    aru
    0.29
    åĦ¿
    0.27
     pathways
    0.27
    æĻºéĢł
    0.27
    å°¼åħĭ
    0.26
    /block
    0.26
     rom
    0.25
    зÑĭва
    0.25
    åĩĨ
    0.25
    åĩĨç¡®æĢ§
    0.25
    Activations Density 12.700%

    No Known Activations

    This feature has no known activations.