© 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. 5404
    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
    eso
    -0.25
    ç«¿
    -0.24
     dist
    -0.24
    çłģ
    -0.24
    Mate
    -0.24
     гÑĢ
    -0.23
    .qq
    -0.23
    å¤ļ家
    -0.23
    Near
    -0.23
    .Material
    -0.23
    POSITIVE LOGITS
    @class
    0.28
     scant
    0.25
    -leaning
    0.25
    .cons
    0.24
    ases
    0.24
    é¢Ĥ
    0.24
    æĬ½è±¡
    0.24
    FTER
    0.24
    appers
    0.23
    æĬ½å¥ĸ
    0.23
    Activations Density 0.043%

    No Known Activations

    This feature has no known activations.