© 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. 7061
    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
    ÅĽÄĩ
    -0.28
    第ä¸Ģ个
    -0.25
     randint
    -0.25
    çİĭçĪ·
    -0.24
    owie
    -0.23
    å¾Ī满æĦı
    -0.23
    æĦı大
    -0.23
    ellidos
    -0.23
    eria
    -0.23
    &T
    -0.23
    POSITIVE LOGITS
    -my
    0.28
    åĬ¡
    0.28
    ê±°
    0.26
     ê±°
    0.26
    ỳ
    0.25
    æĬ±
    0.25
    ä¸Ńæŀ¢
    0.23
    pong
    0.23
    pons
    0.23
     crow
    0.23
    Activations Density 0.044%

    No Known Activations

    This feature has no known activations.