© 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. 141897
    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
    IRM
    -0.26
    楼ä¸ĭ
    -0.25
    RARY
    -0.25
    mentation
    -0.25
    eria
    -0.24
    hma
    -0.24
    plementation
    -0.24
    essment
    -0.24
    Ĺı
    -0.23
    Snake
    -0.23
    POSITIVE LOGITS
    èį¥
    0.28
    nullptr
    0.27
    ót
    0.27
    åįģæĿ¡
    0.26
    uned
    0.25
    å°Ħ
    0.25
     déco
    0.25
    iT
    0.24
    OperationException
    0.24
     shot
    0.24
    Activations Density 23.927%

    No Known Activations

    This feature has no known activations.