© 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. 5343
    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
    ndata
    -0.27
    è¬ĩ
    -0.25
     eye
    -0.25
     SMS
    -0.24
    witter
    -0.24
    æ¼Ĥ
    -0.23
    SJ
    -0.23
     sketch
    -0.23
     LENG
    -0.23
     stew
    -0.23
    POSITIVE LOGITS
    èħĶ
    0.29
    [](
    0.27
    lator
    0.25
     correlation
    0.24
    laces
    0.24
     Suddenly
    0.24
    æ±
    0.24
    ãĤĤãĤĬ
    0.24
    çĦ¶æĺ¯
    0.24
    principal
    0.23
    Activations Density 1.050%

    No Known Activations

    This feature has no known activations.