© 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. 134
    Prev
    Next
    INDEX
    Explanations

    create

    np_max-act · gemini-2.0-flash
    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
     Weiner
    -0.26
    amed
    -0.26
     medi
    -0.26
    inet
    -0.26
    _errors
    -0.26
     Milit
    -0.26
     nowadays
    -0.25
    çĨĬçĮ«
    -0.25
     Fore
    -0.25
     rather
    -0.24
    POSITIVE LOGITS
    otas
    0.29
    erd
    0.28
    ãi
    0.28
     ours
    0.26
    è±ģ
    0.24
    .Must
    0.24
     overd
    0.23
     addCriterion
    0.23
    ç»Ń
    0.23
    utes
    0.23
    Activations Density 1.034%

    No Known Activations