© 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. 64403
    Prev
    Next
    INDEX
    Explanations

    documents, files, or code

    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
    éªĮ
    -0.32
     Pins
    -0.28
    ÑĥÑĪ
    -0.27
    iets
    -0.26
    ä¼¼çļĦ
    -0.26
    ÑĥÑĪки
    -0.26
    åĸĦ
    -0.24
    =no
    -0.24
    tracted
    -0.24
    -comm
    -0.24
    POSITIVE LOGITS
    rez
    0.29
    irut
    0.28
     ([]
    0.27
    çķ¹
    0.27
    opsy
    0.27
    管å±Ģ
    0.25
     initializing
    0.25
    ertz
    0.25
    bove
    0.25
    .cc
    0.24
    Activations Density 9.413%

    No Known Activations