© 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. 25-TRANSCODER-HP
    7. 107249
    Prev
    Next
    INDEX
    Explanations

    prayer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĶĭ
    -0.31
    probe
    -0.29
    æĭIJ
    -0.26
     Pike
    -0.26
     probe
    -0.26
    Dup
    -0.25
     Savage
    -0.25
     remodel
    -0.24
    èŀºä¸Ŀ
    -0.24
     Embedded
    -0.24
    POSITIVE LOGITS
     prayers
    0.66
     prayer
    0.66
    祷
    0.64
    ç¥Ī祷
    0.60
     prayed
    0.57
     Prayer
    0.54
     praying
    0.54
    ç¥Ī
    0.52
     pray
    0.52
    诵
    0.44
    Activations Density 1.028%

    No Known Activations