© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6085
    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
    agu
    -0.30
    asco
    -0.27
    bos
    -0.27
    éĻŀ
    -0.27
     repaint
    -0.27
    马åĬĽ
    -0.26
     gó
    -0.26
    顶éĥ¨
    -0.25
    strup
    -0.25
    AGIC
    -0.25
    POSITIVE LOGITS
    á»ĭ
    0.30
    avr
    0.28
    Private
    0.28
     circuit
    0.26
    culated
    0.26
     Private
    0.26
    `\
    0.26
    ee
    0.26
    æĮĤçīĮ
    0.25
    olving
    0.25
    Activations Density 0.129%

    No Known Activations

    This feature has no known activations.