© 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. 33-TRANSCODER-HP
    7. 54627
    Prev
    Next
    INDEX
    Explanations

    Political/News Context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æŃ¥æŃ¥
    -0.33
    Living
    -0.30
     living
    -0.29
    æĶ»åĬ¿
    -0.29
    rophic
    -0.28
    living
    -0.28
    ië
    -0.26
     voyage
    -0.26
     Living
    -0.25
    beck
    -0.25
    POSITIVE LOGITS
     hold
    0.35
    ukt
    0.29
     ruled
    0.29
    ADOW
    0.28
     rat
    0.28
     ans
    0.28
     holds
    0.28
     handle
    0.27
     org
    0.27
     ent
    0.27
    Activations Density 0.056%

    No Known Activations