© 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. 6070
    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
    ograms
    -0.26
     tá»ij
    -0.26
    culus
    -0.25
    ики
    -0.24
    ç¡®å®ļ
    -0.24
    posable
    -0.24
    nets
    -0.23
    à¸ģà¸ģ
    -0.23
    æĮĩåĩº
    -0.23
    inc
    -0.23
    POSITIVE LOGITS
     wed
    0.30
    ws
    0.26
    ç¢į
    0.26
    ("$.
    0.25
    ”),
    0.25
    被éªĹ
    0.25
    assen
    0.25
    ylon
    0.25
    rss
    0.25
    vertime
    0.25
    Activations Density 0.382%

    No Known Activations

    This feature has no known activations.