© 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. 64221
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    utzer
    -0.26
    åįĬ
    -0.26
    满
    -0.25
    IFIER
    -0.25
    çĮ®
    -0.25
    -0.24
    ä¸ĢåįĬ
    -0.24
     (--
    -0.24
     HALF
    -0.24
    èĩªæľī
    -0.24
    POSITIVE LOGITS
    åı£ä¸Ń
    0.26
     crest
    0.26
     sar
    0.26
    管å§Ķä¼ļ
    0.25
     start
    0.24
    çĶŁäº§æĢ»åĢ¼
    0.24
    richt
    0.24
    å¨Ľ
    0.23
    rift
    0.23
    并åIJij
    0.23
    Activations Density 1.985%

    No Known Activations