© 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. 131
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    brush
    -0.25
    æݩ饰
    -0.23
    æıIJ示
    -0.23
    alt
    -0.23
    ниÑĨа
    -0.22
    ợ
    -0.22
    æİ©
    -0.22
    èĬ
    -0.22
    avic
    -0.22
    ä¸Ńéĵģ
    -0.22
    POSITIVE LOGITS
     sole
    0.26
     Institutions
    0.25
     installation
    0.23
     Emmy
    0.23
     institution
    0.23
     German
    0.22
    sender
    0.22
    _sender
    0.21
     :
    0.21
     sender
    0.21
    Activations Density 0.058%

    No Known Activations