© 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. 58564
    Prev
    Next
    INDEX
    Explanations

    breaking rules

    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
    acam
    -0.28
    agina
    -0.27
     desk
    -0.27
    -pad
    -0.27
     dine
    -0.27
     neuroscience
    -0.26
    infra
    -0.26
    çľĭçĹħ
    -0.26
    zug
    -0.26
     Zug
    -0.26
    POSITIVE LOGITS
     disob
    0.29
    oard
    0.27
    rules
    0.27
    hell
    0.26
     rules
    0.26
     RULE
    0.26
     violated
    0.26
    Rules
    0.26
    _rules
    0.26
     taught
    0.25
    Activations Density 0.004%

    No Known Activations