© 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. 6342
    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
     StringTokenizer
    -0.27
    veloper
    -0.27
    ipur
    -0.26
     "***
    -0.25
    PropertyChanged
    -0.25
    åĪĽå»º
    -0.25
    åħ´ä¸ļ
    -0.25
    RICS
    -0.24
     åĪĽå»º
    -0.24
     Quit
    -0.23
    POSITIVE LOGITS
    ording
    0.30
    good
    0.29
    æīĭä¸ĭ
    0.28
    ules
    0.28
    grand
    0.27
     grand
    0.27
    sent
    0.27
    disc
    0.27
     wholes
    0.27
    ä¸Ĭæĸ¹
    0.27
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.