© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6949
    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
     Ef
    -0.28
     eternity
    -0.26
     sanitizer
    -0.25
    æīĵäºĨ
    -0.25
     Colony
    -0.25
    gence
    -0.24
    æł¸
    -0.24
     colony
    -0.24
    panic
    -0.24
     Lumia
    -0.24
    POSITIVE LOGITS
    ang
    0.27
    éĺ´
    0.27
    çŁ£
    0.26
    plit
    0.26
     TAS
    0.25
    åħļç»Ħ书记
    0.25
    åIJ¬åıĸ
    0.25
     trá»Ŀi
    0.25
    æĺİçŁ¥
    0.25
    æĤ¬æĮĤ
    0.25
    Activations Density 0.045%

    No Known Activations

    This feature has no known activations.