© 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. 20-TRANSCODER-HP
    7. 142453
    Prev
    Next
    INDEX
    Explanations

    Christianity and churches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nde
    -0.28
    .JsonProperty
    -0.27
    instant
    -0.26
    Marsh
    -0.25
    csr
    -0.25
    orial
    -0.24
    achu
    -0.24
     mines
    -0.24
    tri
    -0.24
    ç«ĭåĪ»
    -0.24
    POSITIVE LOGITS
    /lgpl
    0.25
     courte
    0.24
    ä½ľåĵģåĨħ容
    0.24
    é¢Ĩ导人
    0.24
     Purple
    0.23
    sell
    0.23
    ä¹ľ
    0.23
    born
    0.23
    ä¸įæŃ¢
    0.22
    è¼Ķ
    0.22
    Activations Density 12.459%

    No Known Activations