© 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. 130066
    Prev
    Next
    INDEX
    Explanations

    to

    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
    å®£ä¼łæ´»åĬ¨
    -0.30
     Byrne
    -0.28
     Boeh
    -0.26
     grace
    -0.25
    å§Ķå®£ä¼ł
    -0.24
    æº
    -0.24
    abb
    -0.24
    æĬ½è±¡
    -0.23
    $",
    -0.23
     ECB
    -0.23
    POSITIVE LOGITS
    ãģªãĤĤãģ®
    0.28
    ç²¾åįİ
    0.26
    USAGE
    0.25
     days
    0.24
     yellow
    0.24
    ä»°
    0.24
    péri
    0.24
    ñana
    0.24
     USAGE
    0.23
     widths
    0.23
    Activations Density 36.982%

    No Known Activations