© 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. 54566
    Prev
    Next
    INDEX
    Explanations

    /h and -h

    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
     partial
    -0.32
    æĬij
    -0.32
     frag
    -0.26
    æľīæĿ¡ä»¶
    -0.25
    partial
    -0.25
    éŃĶ
    -0.25
     lamb
    -0.24
    强è¡Į
    -0.24
    onta
    -0.24
    DB
    -0.24
    POSITIVE LOGITS
    è°ĥ
    0.28
    rones
    0.28
    ettle
    0.27
    Talk
    0.26
    調
    0.26
    ä¾ı
    0.25
    emean
    0.24
    人æīį
    0.24
    zman
    0.24
     Anderson
    0.24
    Activations Density 0.023%

    No Known Activations