© 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. 6347
    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
    vip
    -0.28
     BUG
    -0.25
    è®·
    -0.24
    izar
    -0.24
     walkers
    -0.24
    æ®Ĭ
    -0.24
    mega
    -0.23
     volunteers
    -0.23
    _elapsed
    -0.23
     squ
    -0.23
    POSITIVE LOGITS
     tens
    0.27
    etypes
    0.25
    .Qt
    0.25
    å±Ģå±Ģéķ¿
    0.24
    çİĭæľĿ
    0.24
    两æīĭ
    0.24
     fascist
    0.24
    两åı¥
    0.24
    士
    0.24
    çĪ·
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.