© 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. 81
    Prev
    Next
    INDEX
    Explanations

    ser

    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
    олÑı
    -0.29
    iple
    -0.25
    ymes
    -0.24
    ics
    -0.24
     века
    -0.24
    ÅĽci
    -0.23
    ation
    -0.23
    vented
    -0.23
    shal
    -0.23
    contro
    -0.23
    POSITIVE LOGITS
    erot
    0.29
     \↵↵
    0.26
     predefined
    0.23
     concat
    0.23
     Bes
    0.22
    amu
    0.22
     {}).
    0.22
     hubs
    0.22
     __________________↵↵
    0.22
    pot
    0.21
    Activations Density 0.054%

    No Known Activations