© 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. 149142
    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
    xEC
    -0.29
    leck
    -0.27
     convention
    -0.26
     iota
    -0.25
    ipo
    -0.24
    ç¥ĸåĽ½
    -0.24
    develop
    -0.24
     losing
    -0.24
     strategically
    -0.24
    æĹłè¾ľ
    -0.24
    POSITIVE LOGITS
    代åĬŀ
    0.26
    trägt
    0.26
     Age
    0.24
    atable
    0.24
    é¾Ħ
    0.23
     perc
    0.23
     Regina
    0.23
    ç»ĵå©ļ
    0.23
    apes
    0.23
    asi
    0.23
    Activations Density 0.695%

    No Known Activations

    This feature has no known activations.