© 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. 142410
    Prev
    Next
    INDEX
    Explanations

    1700s dates

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .nasa
    -0.27
    çĸŁ
    -0.25
    æĥij
    -0.25
    çİ°åĩº
    -0.25
    è¯Ŀé¢ĺ
    -0.24
    warts
    -0.24
     CDDL
    -0.24
    unfold
    -0.24
    SCALE
    -0.24
    onaut
    -0.24
    POSITIVE LOGITS
    Dash
    0.27
     lots
    0.26
    æµģåĬ¨æĢ§
    0.25
     fine
    0.25
    äº
    0.25
    oved
    0.25
     McM
    0.24
    éĢIJ
    0.24
    fine
    0.24
    igin
    0.23
    Activations Density 11.603%

    No Known Activations