© 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. 108714
    Prev
    Next
    INDEX
    Explanations

    Time periods

    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
    utely
    -0.27
    ELY
    -0.26
    eras
    -0.26
    ayer
    -0.25
     concurrently
    -0.25
    æĽ´å¤ļçļĦ
    -0.24
     familiar
    -0.24
    COMMON
    -0.24
    ordion
    -0.23
     entend
    -0.23
    POSITIVE LOGITS
    å¦Ĥæŀľä¸į
    0.29
    lük
    0.28
    (Sub
    0.26
    ãıĦ
    0.25
    /status
    0.25
    ä¸ĭä¸Ģ代
    0.24
     çı
    0.24
    第äºĮ大
    0.24
    infos
    0.24
    è¶ħ
    0.24
    Activations Density 11.686%

    No Known Activations