© 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. 30-TRANSCODER-HP
    7. 96885
    Prev
    Next
    INDEX
    Explanations

    Religious texts and references to God

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    orate
    -0.28
    è¡ĮæĿİ
    -0.26
     innocence
    -0.26
    izable
    -0.26
    áºŃn
    -0.25
    located
    -0.25
    é«ij
    -0.25
    omatic
    -0.24
    èİł
    -0.24
     tuition
    -0.24
    POSITIVE LOGITS
    u
    0.31
    éĢĴ
    0.30
     Alone
    0.29
    æĿ¡ä»¶ä¸ĭ
    0.27
    uw
    0.27
    çĭ¬
    0.26
     alone
    0.26
    çĥ«
    0.25
    cm
    0.25
     sweep
    0.25
    Activations Density 0.885%

    No Known Activations