© 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. 5435
    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
    ìĭŃ
    -0.30
    æŧ
    -0.26
    两çĤ¹
    -0.26
    esz
    -0.25
    åijĭ
    -0.25
    do
    -0.25
    æĺ¯ä»Ģä¹Īåij¢
    -0.24
     old
    -0.24
    ATO
    -0.24
    comm
    -0.24
    POSITIVE LOGITS
    ä¸įå¼Ģ
    0.28
    åģĥ
    0.27
     derog
    0.26
    MSN
    0.26
    richt
    0.25
    istream
    0.25
    DataRow
    0.25
     HIM
    0.25
    åºĸ
    0.24
    ajaran
    0.24
    Activations Density 0.881%

    No Known Activations

    This feature has no known activations.