© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 131095
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    chen
    -0.27
    ail
    -0.25
    ضاء
    -0.25
     Operating
    -0.25
    潦
    -0.24
     disen
    -0.24
    oby
    -0.23
    utzer
    -0.23
    èĢIJçĶ¨
    -0.23
    @Test
    -0.23
    POSITIVE LOGITS
    ió
    0.28
    Tem
    0.25
    èľĤèľľ
    0.25
    تأ
    0.24
     Tem
    0.24
    Allocator
    0.24
     tempList
    0.23
    è¿ĻçĤ¹
    0.23
    .Rel
    0.23
    éĤ¦
    0.23
    Activations Density 5.631%

    No Known Activations

    This feature has no known activations.