© 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. 6095
    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
    æı£
    -0.25
    lat
    -0.25
     Cats
    -0.25
    uding
    -0.24
     ZIP
    -0.24
     meant
    -0.24
    论
    -0.23
    è¿Ļ个è¯į
    -0.23
    ²
    -0.23
    ToFit
    -0.23
    POSITIVE LOGITS
    erview
    0.28
    æ¶ij
    0.27
    apy
    0.26
    urable
    0.26
    quam
    0.25
     favourites
    0.25
    urch
    0.25
    aviour
    0.25
    ester
    0.25
    Enumerable
    0.25
    Activations Density 0.225%

    No Known Activations

    This feature has no known activations.