© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142218
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubar
    -0.30
    ksz
    -0.27
    宵
    -0.26
    _weak
    -0.26
    nio
    -0.25
    ISTR
    -0.25
    INO
    -0.24
    注æĦı
    -0.24
    åį°
    -0.24
    _ob
    -0.24
    POSITIVE LOGITS
     Fate
    0.27
    å¹
    0.26
    */,
    0.25
    zych
    0.25
    .mipmap
    0.25
    sov
    0.24
     CES
    0.24
    éªħ
    0.24
    >-->↵
    0.23
     ìĦ
    0.23
    Activations Density 26.642%

    No Known Activations

    This feature has no known activations.