© 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. 8687
    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
     Encode
    -0.28
    ä¼¼
    -0.26
    SEND
    -0.25
    .sendFile
    -0.25
    Listing
    -0.25
    ENSE
    -0.24
    é½IJé²ģ
    -0.24
    market
    -0.23
     Donation
    -0.23
     te
    -0.23
    POSITIVE LOGITS
    led
    0.30
     Lies
    0.28
    èį·
    0.27
    tür
    0.25
    èģ¿
    0.25
    å¬ĸ
    0.25
    æĿĥéĩį
    0.25
    å¾Ĵ
    0.25
    æĸ½
    0.25
    oker
    0.24
    Activations Density 0.084%

    No Known Activations

    This feature has no known activations.