© 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. 20-TRANSCODER-HP
    7. 131040
    Prev
    Next
    INDEX
    Explanations

    Punctuation and "and"

    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
    Negative Logits
     {}.
    -0.28
    å¦Ĥæŀľæľī
    -0.28
    brit
    -0.27
     ideally
    -0.26
    éī´
    -0.25
    DET
    -0.25
    ools
    -0.25
    磾
    -0.24
    lev
    -0.23
     hoped
    -0.23
    POSITIVE LOGITS
    ushi
    0.32
    å½¢å¼ı
    0.29
     interference
    0.27
    çļĦå½¢å¼ı
    0.27
    /forms
    0.26
    è°¢éĤĢ
    0.25
    äºĮåįģåĽĽ
    0.25
    ieux
    0.25
    icamente
    0.24
    å¹²é¢Ħ
    0.24
    Activations Density 57.831%

    No Known Activations