© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40413
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gap
    -0.27
    å·²å®ĮæĪIJ
    -0.27
    .spi
    -0.26
     Gap
    -0.26
    .prot
    -0.26
    Ñīин
    -0.25
    .internal
    -0.25
    lip
    -0.24
    èį·
    -0.24
    Collapse
    -0.24
    POSITIVE LOGITS
    çĮ¥
    0.25
    POOL
    0.25
     objs
    0.25
    edes
    0.24
    umbs
    0.24
    -band
    0.24
    oulouse
    0.24
    Pager
    0.24
     insanity
    0.23
    udio
    0.23
    Activations Density 0.128%

    No Known Activations

    This feature has no known activations.