© 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. 19806
    Prev
    Next
    INDEX
    Explanations

    Programming

    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
     Sight
    -0.27
    RAR
    -0.26
    è§Ĩ
    -0.26
    èĸ®
    -0.26
     sighting
    -0.25
    å®ļäºĨ
    -0.25
    åĩŃ
    -0.25
    escort
    -0.25
    åı¸
    -0.24
    å®
    -0.24
    POSITIVE LOGITS
    è£Ĥ
    0.30
     master
    0.29
    .master
    0.29
     Programming
    0.28
     programming
    0.27
    prototype
    0.27
     engineer
    0.26
    建
    0.26
     hyper
    0.26
    Code
    0.26
    Activations Density 1.198%

    No Known Activations