© 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. 5946
    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
    第ä¸ī代
    -0.33
    formats
    -0.30
    full
    -0.29
    Full
    -0.28
     Full
    -0.28
    ãĥķãĥ«
    -0.28
    erman
    -0.26
    erd
    -0.26
    ed
    -0.26
     full
    -0.25
    POSITIVE LOGITS
    ĥģ
    0.28
    æIJģ
    0.25
    warf
    0.25
    åįĥæĸ¹çĻ¾
    0.24
    ìĩ¼
    0.23
     Rough
    0.23
    ä¸Ĭåİ»
    0.23
     ownerId
    0.23
    idas
    0.23
    itioner
    0.23
    Activations Density 0.160%

    No Known Activations

    This feature has no known activations.