© 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. 20-TRANSCODER-HP
    7. 131148
    Prev
    Next
    INDEX
    Explanations

    Code/website related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    客
    -0.27
    说åĩºæĿ¥
    -0.25
    éĤ£æł·
    -0.25
     Reach
    -0.25
     slik
    -0.25
    ISTS
    -0.24
    ÃŃst
    -0.24
     reach
    -0.24
    presso
    -0.24
    ìĹł
    -0.24
    POSITIVE LOGITS
     Ngh
    0.27
     maxWidth
    0.24
    .strptime
    0.24
    æ´ĭæ´ĭ
    0.23
    ufe
    0.23
    éªĿ
    0.23
    _behavior
    0.23
    localStorage
    0.23
    azine
    0.23
     ranch
    0.23
    Activations Density 0.957%

    No Known Activations