© 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. 151344
    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
     Rs
    -0.29
     duy
    -0.27
    ailand
    -0.27
    Rs
    -0.26
    oy
    -0.26
    íģIJ
    -0.26
    ŃIJ
    -0.26
    诰
    -0.24
    ahi
    -0.24
    ISIBLE
    -0.24
    POSITIVE LOGITS
     uses
    0.27
     reasons
    0.26
    çļĦåİŁåĽł
    0.26
    reason
    0.25
     WHATSOEVER
    0.25
    åİŁåĽł
    0.25
     ap
    0.25
     Len
    0.25
    aper
    0.24
     Storm
    0.24
    Activations Density 0.075%

    No Known Activations

    This feature has no known activations.