© 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. 6748
    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
    italize
    -0.27
    lut
    -0.25
    itic
    -0.25
    Dimensions
    -0.24
     Titles
    -0.24
    official
    -0.24
    season
    -0.24
    ìŀĶ
    -0.24
    ä¸Ĭ游
    -0.23
    adder
    -0.23
    POSITIVE LOGITS
    spe
    0.28
    je
    0.25
    кл
    0.25
     manoe
    0.24
    oe
    0.23
    ãĤ¸ãĤ§
    0.23
    spell
    0.23
     pardon
    0.23
     пом
    0.23
     works
    0.22
    Activations Density 0.045%

    No Known Activations

    This feature has no known activations.