© 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
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 6133
    Prev
    Next
    INDEX
    Explanations

    contractions

    np_max-act · gemini-2.0-flash
    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
    {
    -0.34
    (
    -0.30
    "
    -0.30
    ing
    -0.29
    '
    -0.29
    ary
    -0.28
    er
    -0.28
    å°±æĺ¯
    -0.27
    [
    -0.27
    i
    -0.27
    POSITIVE LOGITS
    ities
    0.46
    ÂŃing
    0.27
    ively
    0.24
    -ever
    0.23
    åľ¨èģĮ
    0.23
    ´t
    0.23
    <![
    0.22
    说æĺ¯
    0.21
    ForResource
    0.21
    nett
    0.21
    Activations Density 8.466%

    No Known Activations