© 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. 52668
    Prev
    Next
    INDEX
    Explanations

    universities and colleges

    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
    èįī
    -0.27
    MinMax
    -0.26
    -Out
    -0.26
    åĬ¨æīĭ
    -0.26
     AAP
    -0.25
     bree
    -0.24
    èĬ
    -0.24
     manh
    -0.24
    OfWork
    -0.24
    ä¸Ģ举
    -0.23
    POSITIVE LOGITS
    izza
    0.28
    lined
    0.28
    hev
    0.25
     halk
    0.24
     packing
    0.24
     hak
    0.24
    sets
    0.24
    pling
    0.24
    æĬ«
    0.24
    chaft
    0.23
    Activations Density 0.011%

    No Known Activations