© 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. 131115
    Prev
    Next
    INDEX
    Explanations

    Single digit numbers

    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
    è§ģ
    -0.32
     sez
    -0.27
    GENCY
    -0.25
    ibil
    -0.25
    uci
    -0.25
    جد
    -0.25
    åħ¬ç¤º
    -0.25
     focusing
    -0.25
    æĸĩæĺİ
    -0.24
    æĸĩæ¡£
    -0.24
    POSITIVE LOGITS
    lettes
    0.31
    åħį
    0.27
    entic
    0.26
    ãĥģãĤ§
    0.26
    annon
    0.25
    etting
    0.25
    ç»Ŀç¼ĺ
    0.25
     prepaid
    0.25
    reas
    0.25
    aden
    0.25
    Activations Density 7.342%

    No Known Activations