© 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. 141883
    Prev
    Next
    INDEX
    Explanations

    Code/URLs/File paths

    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
    åįıä¼ļä¼ļåijĺ
    -0.32
    éĤ£äºĽ
    -0.31
    ucs
    -0.26
    CIÃĵN
    -0.25
    opia
    -0.25
    æĦŁåħ´è¶£çļĦ
    -0.25
     ringing
    -0.24
    ses
    -0.24
     jub
    -0.24
    çļĦçľ¼
    -0.24
    POSITIVE LOGITS
    /options
    0.28
     '\'
    0.27
    idis
    0.26
     Balt
    0.25
    wner
    0.25
    åİĭåĪ¶
    0.25
    çªģå¦Ĥ
    0.25
    ä¸ŃæĸŃ
    0.25
    PageIndex
    0.24
    irá
    0.23
    Activations Density 2.240%

    No Known Activations