© 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. 5112
    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
    è°ĥ
    -0.26
     intrinsic
    -0.26
     mại
    -0.25
     Ñģобой
    -0.25
     tail
    -0.25
     Clay
    -0.25
     whereas
    -0.25
    Completion
    -0.24
     Whereas
    -0.24
     Completion
    -0.23
    POSITIVE LOGITS
     ${↵
    0.30
    erate
    0.29
    竦
    0.25
    çļĦ帮åĬ©ä¸ĭ
    0.25
    åĽŀé¦Ī
    0.24
    è¹Ī
    0.24
     chù
    0.23
    泪水
    0.23
     doch
    0.23
    _#{
    0.23
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.