© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56379
    Prev
    Next
    INDEX
    Explanations

    words similar to "while"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rowse
    -0.26
    ats
    -0.25
    ét
    -0.25
    eps
    -0.25
    été
    -0.24
    åıijè§ī
    -0.23
    Parcel
    -0.23
    #\
    -0.23
    .asset
    -0.23
    аж
    -0.22
    POSITIVE LOGITS
     while
    1.41
    while
    1.30
     While
    1.23
    èĢĮ
    1.20
    While
    1.17
    	while
    1.15
     whereas
    1.11
     whilst
    1.07
     mentre
    1.02
     WHILE
    0.99
    Activations Density 0.003%

    No Known Activations