© 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. 5953
    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
    owitz
    -0.26
     viewing
    -0.26
    umb
    -0.26
     com
    -0.25
    UMB
    -0.24
     prov
    -0.24
    =com
    -0.23
     revealing
    -0.23
     spirits
    -0.23
    姿
    -0.23
    POSITIVE LOGITS
    æºħ
    0.29
    éĶĢåĶ®æĶ¶åħ¥
    0.27
    çłĶ
    0.24
    å¤ļä¹Ī
    0.24
    erten
    0.23
    uers
    0.23
    erule
    0.23
    Thrown
    0.23
    .old
    0.23
    illage
    0.23
    Activations Density 0.027%

    No Known Activations

    This feature has no known activations.