© 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. 14-TRANSCODER-HP
    7. 39606
    Prev
    Next
    INDEX
    Explanations

    variations of verb "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    worth
    -0.32
    éĢīåĿĢ
    -0.29
    fo
    -0.27
    åĵī
    -0.25
     befind
    -0.25
    .swt
    -0.24
    ãĤıãĤĮ
    -0.24
     removeFrom
    -0.24
     sift
    -0.24
    zeichnet
    -0.23
    POSITIVE LOGITS
    åħ¬å®īéĥ¨
    0.26
     purs
    0.26
    æĢ»å±Ģ
    0.26
    RG
    0.25
    樯
    0.25
    itis
    0.25
    forme
    0.25
    rg
    0.25
     rg
    0.24
     giorn
    0.24
    Activations Density 0.362%

    No Known Activations