© 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. 64703
    Prev
    Next
    INDEX
    Explanations

    Code, comments, metadata snippets

    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
    mine
    -0.26
     CASE
    -0.26
    amil
    -0.26
    åģı
    -0.24
     Came
    -0.24
    派驻
    -0.24
     Hab
    -0.24
     apro
    -0.24
     CP
    -0.24
    èĢĮè¨Ģ
    -0.24
    POSITIVE LOGITS
    ué
    0.27
    ió
    0.26
    tie
    0.25
    ä¸įä¸Ĭ
    0.25
    è¿ĻæĿ¡è·¯
    0.24
    aan
    0.24
    ece
    0.23
    ä½Ĩè¿Ļ
    0.23
    uguay
    0.23
    ýt
    0.23
    Activations Density 1.852%

    No Known Activations