© 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. 31-TRANSCODER-HP
    7. 19935
    Prev
    Next
    INDEX
    Explanations

    variations of the word "come"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     about
    -0.28
    eor
    -0.26
    eft
    -0.25
    about
    -0.25
    erce
    -0.25
     Eg
    -0.24
    orz
    -0.23
    verige
    -0.23
    ToLeft
    -0.23
     propelled
    -0.23
    POSITIVE LOGITS
     comes
    0.40
    came
    0.39
     came
    0.38
    åĩºæĿ¥
    0.37
     come
    0.36
     Comes
    0.35
    åĩºæĿ¥äºĨ
    0.35
     coming
    0.35
    comes
    0.33
    come
    0.32
    Activations Density 1.370%

    No Known Activations