© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5352
    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
    reation
    -0.27
    ımı
    -0.25
    impan
    -0.25
    lian
    -0.25
    esor
    -0.25
    '+↵
    -0.25
    immers
    -0.25
    itone
    -0.25
    ÙħÙĬÙĦ
    -0.24
    emade
    -0.24
    POSITIVE LOGITS
     Gol
    0.26
    ment
    0.26
    é¦ĸåħĪè¦ģ
    0.25
     post
    0.25
    .getItem
    0.25
     formerly
    0.25
    å¦Ĥä½ķ
    0.25
     finalize
    0.24
    getItem
    0.24
     future
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.