© 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. 23-TRANSCODER-HP
    7. 25473
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    unda
    -0.27
    tabl
    -0.25
    icide
    -0.25
    åĽŀ家
    -0.24
     clocks
    -0.24
    igion
    -0.24
    ster
    -0.23
    ials
    -0.23
    çIJĨ
    -0.23
    家å±ħ
    -0.23
    POSITIVE LOGITS
    scheduled
    0.28
    å°ijäºĨ
    0.27
    åĮºç®¡å§Ķä¼ļ
    0.27
     addslashes
    0.24
    å±Ģåī¯å±Ģéķ¿
    0.24
     scheduled
    0.24
    lops
    0.24
    år
    0.24
    bindValue
    0.23
    esub
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.