© 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. 40365
    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
    igraphy
    -0.28
     fat
    -0.26
     dom
    -0.25
    DON
    -0.25
     biom
    -0.24
    [column
    -0.24
     trust
    -0.24
     captures
    -0.24
    .configure
    -0.24
     destin
    -0.24
    POSITIVE LOGITS
    ynchronously
    0.28
    ictured
    0.26
    onis
    0.25
    è¢Ń
    0.25
     superficial
    0.25
     Conrad
    0.25
     searchable
    0.25
    å°´å°¬
    0.24
    RelativeTo
    0.24
    åįģåĪĨéĴŁ
    0.24
    Activations Density 0.357%

    No Known Activations

    This feature has no known activations.