© 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. 8430
    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
     retire
    -0.28
     jour
    -0.26
    売
    -0.26
    带ä¸Ĭ
    -0.26
     commerce
    -0.25
     markup
    -0.25
     cle
    -0.24
     discard
    -0.24
     mandates
    -0.23
    çĥ·
    -0.23
    POSITIVE LOGITS
    ERO
    0.27
    车åŀĭ
    0.25
     DNC
    0.25
     Herc
    0.25
    ´t
    0.24
    çIJĥåľº
    0.24
    çĶŁæĢķ
    0.24
     Spa
    0.23
     Soccer
    0.23
    .loaded
    0.23
    Activations Density 0.503%

    No Known Activations

    This feature has no known activations.