© 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. 141742
    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
    LBL
    -0.28
    æīĢ以说
    -0.25
    çĦ¶åIJİåĨį
    -0.25
    ints
    -0.24
    è¿Ļå°±
    -0.23
    Ž
    -0.23
    åIJİåĨį
    -0.23
    YouTube
    -0.23
    åı¯è°ĵ
    -0.23
     Meanwhile
    -0.22
    POSITIVE LOGITS
    mith
    0.28
    datagrid
    0.27
    á»Ń
    0.27
    alth
    0.26
    oppins
    0.26
    dam
    0.24
    ick
    0.24
    коÑģ
    0.24
    ä¸į解
    0.24
    æĤ¬
    0.24
    Activations Density 51.636%

    No Known Activations

    This feature has no known activations.