© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64016
    Prev
    Next
    INDEX
    Explanations

    technical/scientific writing

    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
    èĦĸåŃIJ
    -0.27
    enh
    -0.26
    /start
    -0.26
    ,char
    -0.25
     vest
    -0.25
    è¯ķçĤ¹å·¥ä½ľ
    -0.25
    GNU
    -0.25
    cbd
    -0.24
    oser
    -0.24
    溯æºIJ
    -0.24
    POSITIVE LOGITS
    å¾®åŀĭ
    0.28
    ÃŃlia
    0.28
    igan
    0.27
    æŁIJ个
    0.27
    ências
    0.27
    åľĸ
    0.26
     Adapter
    0.26
     Yayın
    0.26
    Bulletin
    0.26
    æİĸ
    0.26
    Activations Density 37.220%

    No Known Activations