© 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. 32-TRANSCODER-HP
    7. 42658
    Prev
    Next
    INDEX
    Explanations

    variations of the word "build"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ượt
    -0.26
    请çĤ¹åĩ»
    -0.25
    StateChanged
    -0.24
    ÙħÙĬÙĦ
    -0.24
    ç»ıéªĮ丰å¯Į
    -0.24
     genome
    -0.24
     Lage
    -0.24
     Mour
    -0.23
    è¶Ł
    -0.23
    .flip
    -0.23
    POSITIVE LOGITS
     built
    0.44
     Built
    0.39
    .build
    0.39
    Built
    0.35
     build
    0.35
     builders
    0.34
    build
    0.34
    built
    0.31
    	build
    0.30
    .builders
    0.30
    Activations Density 0.001%

    No Known Activations