© 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. 5831
    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
    agus
    -0.29
    ips
    -0.29
    mdat
    -0.28
    aeda
    -0.26
    ystack
    -0.26
     болÑĮÑĪ
    -0.25
    æ·»
    -0.25
     clutch
    -0.25
    .hp
    -0.24
    éĶģ
    -0.24
    POSITIVE LOGITS
    çīĽ
    0.25
    åı¦ä¸ĢåįĬ
    0.25
    åħīæĺİ
    0.25
    èĩªçĦ¶èĢĮ
    0.24
    -comments
    0.24
    çĥĤ
    0.24
    ãģķãĤī
    0.23
     curls
    0.23
    /job
    0.23
     dropped
    0.23
    Activations Density 0.062%

    No Known Activations

    This feature has no known activations.