© 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. 6766
    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
     appeal
    -0.31
    appe
    -0.30
     appealing
    -0.26
     Appeal
    -0.25
    两项
    -0.25
    emes
    -0.25
    éĨħ
    -0.24
     guessed
    -0.24
    asics
    -0.23
    .numpy
    -0.23
    POSITIVE LOGITS
    ilda
    0.30
    è§Ħæł¼
    0.29
    èĥ¸
    0.25
    第ä¸Ģ次
    0.24
    åĭĭ
    0.24
    åħľ
    0.24
    aji
    0.24
    Bron
    0.24
    Ã¤ÃŁ
    0.24
    æѤç§į
    0.24
    Activations Density 1.169%

    No Known Activations

    This feature has no known activations.