© 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. 19989
    Prev
    Next
    INDEX
    Explanations

    Code and configuration files

    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
    5
    -0.32
     inter
    -0.29
     Abe
    -0.28
    im
    -0.28
     terminal
    -0.27
    roys
    -0.27
     param
    -0.26
    8
    -0.26
    ate
    -0.26
     self
    -0.26
    POSITIVE LOGITS
    ndx
    0.31
    è¯ļæĦı
    0.29
    IDX
    0.28
    åħ¬åħ±èµĦæºIJ
    0.27
    åĬĿ
    0.26
    Chelsea
    0.25
    idency
    0.25
    undry
    0.25
    ToDevice
    0.25
    绩
    0.24
    Activations Density 0.331%

    No Known Activations