© 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. 18-TRANSCODER-HP
    7. 88113
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åij³
    -0.29
    imest
    -0.29
    éĿĽ
    -0.28
    ħĮ
    -0.26
    /colors
    -0.25
    uat
    -0.25
    wil
    -0.25
     wil
    -0.24
    HN
    -0.24
    Ñĥгл
    -0.24
    POSITIVE LOGITS
     faithful
    0.27
    wich
    0.27
    åģıå·®
    0.26
    å¼ij
    0.25
    ationally
    0.25
    atorium
    0.24
    åģı
    0.24
    åģıåIJij
    0.23
    ione
    0.23
    copyright
    0.23
    Activations Density 9.277%

    No Known Activations