© 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. 5910
    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
    imity
    -0.29
    ãģıãģł
    -0.28
    ãģĦãģ¤ãĤĤ
    -0.27
     measurement
    -0.25
    åħ¶æ¬¡æĺ¯
    -0.24
    à¸ļาล
    -0.24
     aj
    -0.24
    ä¸ĩ
    -0.24
    æ°´åĪĨ
    -0.23
    家å±ŀ
    -0.23
    POSITIVE LOGITS
    åıĸæļĸ
    0.29
    omb
    0.29
    åĦĨ
    0.28
    KHTML
    0.26
    æĺ¯ä¸Ģ件
    0.25
    radi
    0.24
    umin
    0.24
     Marino
    0.24
    lop
    0.24
     stored
    0.24
    Activations Density 0.357%

    No Known Activations

    This feature has no known activations.