© 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. 5142
    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
     whistlebl
    -0.26
    ÃŃ
    -0.25
     released
    -0.25
     Punk
    -0.24
     vacuum
    -0.24
    tÃŃ
    -0.24
     insign
    -0.23
    ::_
    -0.23
    ÃĵN
    -0.23
    <Role
    -0.23
    POSITIVE LOGITS
    笳
    0.28
    ä¹ĭåĬĽ
    0.26
    orna
    0.26
    iative
    0.25
    çĥ½
    0.24
    ation
    0.24
    esy
    0.24
    -dollar
    0.24
     furry
    0.24
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.24
    Activations Density 0.880%

    No Known Activations

    This feature has no known activations.