© 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. 12-TRANSCODER-HP
    7. 22170
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     shade
    -0.29
    oton
    -0.28
     term
    -0.28
    rown
    -0.27
    brew
    -0.26
    饮çĶ¨
    -0.26
    å§Ķå±Ī
    -0.26
     crowds
    -0.25
    ied
    -0.25
    tracer
    -0.24
    POSITIVE LOGITS
    Profiles
    0.28
    æģ¯æģ¯
    0.27
    imentary
    0.26
     secular
    0.26
     Gecko
    0.26
    webkit
    0.25
    Ptr
    0.25
     profiles
    0.25
    )const
    0.25
    Profiler
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.