© 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. 6947
    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
    ä¸Ĭ游
    -0.31
    plit
    -0.28
    aviest
    -0.26
    upert
    -0.26
    reu
    -0.25
     upstream
    -0.25
    preced
    -0.25
    beiten
    -0.25
    ivity
    -0.24
    å±±ä¸Ĭ
    -0.24
    POSITIVE LOGITS
    EMS
    0.24
    ỵ
    0.24
     licensee
    0.23
    Ä°Z
    0.23
    rouch
    0.23
    incerely
    0.23
    Thought
    0.23
    ccb
    0.23
     denim
    0.23
     pys
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.