© 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. 6547
    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
     trial
    -0.28
    Ease
    -0.27
     sitting
    -0.27
    è¯ķ
    -0.26
    åĬŀçIJĨ
    -0.26
    è¯ķè¯ķ
    -0.25
     release
    -0.25
    çĶ¨æīĭ
    -0.25
     releasing
    -0.25
    istol
    -0.24
    POSITIVE LOGITS
    .deep
    0.28
    etag
    0.27
    nis
    0.27
    cone
    0.26
    .getOwnPropertyDescriptor
    0.26
    âĶħ
    0.26
    åİŁæĿ¥æĺ¯
    0.25
    neau
    0.25
    xdb
    0.25
    bine
    0.25
    Activations Density 0.918%

    No Known Activations

    This feature has no known activations.