© 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
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5979
    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
    ä¸ĩæĪ·
    -0.29
    itez
    -0.29
    çİĩ为
    -0.26
    缩
    -0.26
    unction
    -0.25
    spam
    -0.24
    åı·åı¬
    -0.24
    _LP
    -0.24
     Grave
    -0.24
    欢åij¼
    -0.24
    POSITIVE LOGITS
    little
    0.30
    iel
    0.26
     hại
    0.25
    least
    0.25
    é®
    0.25
     Fischer
    0.24
     little
    0.24
     ass
    0.24
     Spec
    0.23
     Buddhism
    0.23
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.