© 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. 7691
    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
    alin
    -0.26
    RAP
    -0.26
    IRE
    -0.25
    ধ
    -0.25
     Formula
    -0.25
     Termin
    -0.25
    gers
    -0.24
    tre
    -0.24
    iren
    -0.24
     Rog
    -0.24
    POSITIVE LOGITS
     newInstance
    0.31
     passenger
    0.27
    obra
    0.26
     shuttle
    0.26
    BSD
    0.26
    çĶŁçIJĨ
    0.24
     alÄ±ÅŁ
    0.24
    ophysical
    0.24
    奴
    0.24
    åħ¬ä¸»
    0.24
    Activations Density 0.038%

    No Known Activations

    This feature has no known activations.