© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9910
    Prev
    Next
    INDEX
    Explanations

    immune responses and viruses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĻ¨
    -0.27
    Platforms
    -0.27
     agents
    -0.27
     people
    -0.27
    fony
    -0.27
     agent
    -0.27
    Agents
    -0.26
    å·¥ä½ľèĢħ
    -0.26
    涿
    -0.26
    å¤ļåIJį
    -0.26
    POSITIVE LOGITS
    richt
    0.26
    æµ®åĬ¨
    0.24
    å±ģ
    0.24
    ripper
    0.24
    _flat
    0.23
    辫
    0.23
    赶åĪ°
    0.23
    uran
    0.23
    éĹ²ç½®
    0.23
    ĽĦ
    0.23
    Activations Density 0.004%

    No Known Activations