© 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. 289
    Prev
    Next
    INDEX
    Explanations

    medical, scientific research

    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
     Russians
    -0.30
    олоÑģ
    -0.27
     âĨĴ↵↵
    -0.26
    认
    -0.25
     tolerance
    -0.25
     lengths
    -0.24
     nursing
    -0.24
    åĨĽåĽ¢
    -0.23
     sw
    -0.23
     Downs
    -0.23
    POSITIVE LOGITS
    ä¸įä¸Ĭ
    0.26
    embedded
    0.26
    ler
    0.26
    ixo
    0.26
    GN
    0.25
    (Dense
    0.25
    caffold
    0.25
    uste
    0.24
    ç¼ĸ
    0.24
    åĪ¶éĢł
    0.24
    Activations Density 1.137%

    No Known Activations