© 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. 142752
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     flipped
    -0.26
    hir
    -0.26
    eteor
    -0.26
    æľĿ
    -0.25
    à¸ķา
    -0.24
    IBUT
    -0.24
    è¨Ģ
    -0.24
    ırım
    -0.24
     imaginable
    -0.24
    ç¿»
    -0.24
    POSITIVE LOGITS
    amba
    0.28
    Processes
    0.27
     McMahon
    0.26
    getApplication
    0.26
    åĶ¯ä¸ĢçļĦ
    0.26
    ãĤ¸ãĥ¼
    0.25
    agra
    0.24
    ANC
    0.23
    åº
    0.23
    ún
    0.23
    Activations Density 12.651%

    No Known Activations

    This feature has no known activations.