© 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
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 75
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     song
    -0.25
    ÅĽnie
    -0.25
    ä»ĺ
    -0.24
    è·ŁçĿĢ
    -0.24
    posted
    -0.24
    izzly
    -0.24
    æijĬ
    -0.24
    å¼Ģåħ·
    -0.24
     posted
    -0.24
    å¥ı
    -0.24
    POSITIVE LOGITS
    ино
    0.27
    canf
    0.26
    ino
    0.26
    cba
    0.24
    .deb
    0.24
     Consortium
    0.24
    hus
    0.24
    Tes
    0.23
    eb
    0.23
     Bus
    0.23
    Activations Density 0.351%

    No Known Activations

    This feature has no known activations.