© 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. 19962
    Prev
    Next
    INDEX
    Explanations

    Organs and body

    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
     оÑĢг
    -0.28
    доÑĢож
    -0.28
    isd
    -0.27
    ises
    -0.27
     rotational
    -0.27
    sey
    -0.27
    erox
    -0.26
    åºĬä¸Ĭ
    -0.26
    him
    -0.26
     Delegate
    -0.26
    POSITIVE LOGITS
     heart
    0.34
     lÃłnh
    0.33
     sweat
    0.29
     Sweat
    0.28
    lung
    0.28
    å¿ĥ
    0.27
    骨骼
    0.27
     bone
    0.27
    åĶĩ
    0.27
     lungs
    0.27
    Activations Density 0.817%

    No Known Activations