© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4767
    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
    æĭĪ
    -0.28
    nock
    -0.28
    umin
    -0.26
     baÅŁlayan
    -0.26
    åĬŀå®ŀäºĭ
    -0.24
    溲
    -0.24
    éļĻ
    -0.24
    ubre
    -0.24
    _analysis
    -0.24
     departed
    -0.24
    POSITIVE LOGITS
    è§Ħ
    0.26
    vol
    0.25
     lav
    0.25
     San
    0.25
    -san
    0.25
    è¯Ŀ
    0.24
    rok
    0.24
    amation
    0.24
    rov
    0.24
     Af
    0.24
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.