© 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. 24-TRANSCODER-HP
    7. 151214
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    /Area
    -0.26
     Vice
    -0.24
     vice
    -0.24
     ji
    -0.23
    bilt
    -0.23
    obb
    -0.23
     squeez
    -0.23
    绥
    -0.23
    renderer
    -0.22
    enstein
    -0.22
    POSITIVE LOGITS
    Ïĭ
    0.25
    ino
    0.25
     transitioning
    0.24
    xca
    0.23
    ãĤ²
    0.23
    .Mod
    0.23
    黼
    0.23
    åĪĨå±Ģ
    0.23
    乡
    0.22
    /groups
    0.22
    Activations Density 1.120%

    No Known Activations

    This feature has no known activations.