© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39427
    Prev
    Next
    INDEX
    Explanations

    reflection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    pth
    -0.27
    grund
    -0.26
    safe
    -0.26
     safe
    -0.25
    éĿĴ
    -0.25
     Valentine
    -0.25
     Match
    -0.24
    embed
    -0.24
    马路
    -0.23
    asi
    -0.23
    POSITIVE LOGITS
    hamster
    0.28
     chặn
    0.25
    ÙĪØ°
    0.24
    éªĽ
    0.24
    éħİ
    0.24
    .kotlin
    0.24
    دة
    0.24
    åĪĨä¼ļ
    0.23
     Swan
    0.23
     Nicola
    0.23
    Activations Density 0.112%

    No Known Activations