© 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. 5826
    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
    eft
    -0.26
    atts
    -0.26
    .Xaml
    -0.26
    Ľå»º
    -0.26
    eer
    -0.25
    .getLogger
    -0.25
    ável
    -0.25
    orz
    -0.25
    xcd
    -0.25
    _pcm
    -0.25
    POSITIVE LOGITS
     sol
    0.29
    oli
    0.27
    âĢ¦↵
    0.26
    Ready
    0.25
    ढ
    0.25
     Serial
    0.25
    âĢ¦
    0.25
     ↵
    0.25
     Depending
    0.25
    (
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.