© 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. 6896
    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
    ascar
    -0.29
    vents
    -0.27
    icorn
    -0.27
    oused
    -0.26
    å±¥
    -0.25
    ucker
    -0.25
    PATCH
    -0.25
    |string
    -0.24
     anything
    -0.24
    ibles
    -0.24
    POSITIVE LOGITS
     separ
    0.30
    ä¸Ģ缴
    0.26
    гла
    0.24
    -legged
    0.24
    åĪĨ离
    0.24
     Hass
    0.24
    ule
    0.24
    -break
    0.23
    .sep
    0.23
    ä¸Ģ缴æĺ¯
    0.23
    Activations Density 0.872%

    No Known Activations

    This feature has no known activations.