© 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. 31-TRANSCODER-HP
    7. 17917
    Prev
    Next
    INDEX
    Explanations

    Technical/programming texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    NetMessage
    -0.28
     cogn
    -0.28
    模åŀĭ
    -0.28
    ifr
    -0.27
     exception
    -0.27
    uml
    -0.26
     briefed
    -0.26
     weblog
    -0.26
    _cum
    -0.25
    elif
    -0.25
    POSITIVE LOGITS
    èĩªåĬ¨åĮĸ
    0.31
     automatically
    0.29
     automated
    0.29
    Autom
    0.28
    çijķ
    0.28
    autom
    0.27
     Automatically
    0.27
    orro
    0.26
     problematic
    0.26
     flesh
    0.26
    Activations Density 0.964%

    No Known Activations