© 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. 24235
    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
    pron
    -0.28
     affiliated
    -0.27
    .addRow
    -0.26
    åľ©
    -0.26
    -aff
    -0.25
    åıijéŁ³
    -0.25
     Rem
    -0.24
    æľĢ容æĺĵ
    -0.24
    emons
    -0.23
    æĮŁ
    -0.23
    POSITIVE LOGITS
     autob
    0.28
    åľ°éģĵ
    0.26
    æİ©
    0.25
    eneg
    0.25
    untas
    0.25
    éģĵ
    0.24
    桶
    0.24
    _busy
    0.24
    gli
    0.24
    iox
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.