© 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. 7999
    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
    åħ¬åĬŀ
    -0.28
     Stam
    -0.27
    ale
    -0.26
    æĺ¯åIJ¦åŃĺåľ¨
    -0.26
    绣çŃ¹æİ¨è¿Ľ
    -0.26
    åħ¬åħ±æĸĩåĮĸ
    -0.25
    apon
    -0.25
    figcaption
    -0.24
    ertext
    -0.24
    å·®è·Ŀ
    -0.24
    POSITIVE LOGITS
    NEY
    0.26
    neys
    0.26
    sic
    0.24
    (Double
    0.24
    /met
    0.24
    梢
    0.24
    emet
    0.24
    uchi
    0.24
    .struts
    0.23
    xic
    0.23
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.