© 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. 6554
    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
    åĥµ
    -0.28
    åŁİ乡
    -0.27
    è¶ĭ
    -0.27
    asca
    -0.27
    éļıæīĭ
    -0.26
    æĦŁ
    -0.25
    cast
    -0.25
    éĤĢ
    -0.25
    .leave
    -0.24
    è·ĥ
    -0.24
    POSITIVE LOGITS
     volta
    0.28
     fulfill
    0.25
    äºļ马
    0.25
     onStop
    0.25
    è¾ĪåŃIJ
    0.25
    fried
    0.25
     realiz
    0.25
    -transfer
    0.25
    undry
    0.24
     transfer
    0.24
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.