© 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. 19-TRANSCODER-HP
    7. 7906
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imbus
    -0.30
    .sourceforge
    -0.28
    (___
    -0.27
    _void
    -0.24
    паÑĢ
    -0.24
     "<?
    -0.24
     Peb
    -0.24
     Classified
    -0.24
    dfd
    -0.24
    	Class
    -0.23
    POSITIVE LOGITS
    IGO
    0.32
    en
    0.28
    l
    0.28
    NS
    0.27
    o
    0.26
    æĸ¹æīį
    0.26
    lu
    0.25
    åĪ©çĶ¨æĤ¨çļĦ
    0.25
    SF
    0.25
     extensively
    0.25
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.