© 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. 58616
    Prev
    Next
    INDEX
    Explanations

    Religion, beliefs

    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
    å¢ŀå¹ħ
    -0.27
     Margin
    -0.26
     entrega
    -0.25
    ously
    -0.25
    -lib
    -0.25
    ght
    -0.24
    ALTH
    -0.24
    åij¨è½¬
    -0.24
    åIJ¯çĶ¨
    -0.24
    aday
    -0.24
    POSITIVE LOGITS
     religion
    0.30
    ä¿¡ä»°
    0.29
     attitudes
    0.27
    å®ĹæķĻ
    0.27
    ä¸Ńæĸ°
    0.27
    仪å¼ı
    0.27
     fell
    0.27
    emento
    0.27
    fell
    0.27
     Religion
    0.27
    Activations Density 0.001%

    No Known Activations