© 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. 24-TRANSCODER-HP
    7. 149258
    Prev
    Next
    INDEX
    Explanations

    code and technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     blogger
    -0.48
     tweeted
    -0.45
     bloggers
    -0.44
    åįļ客
    -0.44
    Twitter
    -0.44
     blog
    -0.43
     Etsy
    -0.43
     Twitter
    -0.43
     tweets
    -0.42
     blogs
    -0.41
    POSITIVE LOGITS
     Yugoslavia
    0.31
     tapes
    0.31
     tape
    0.31
     cassette
    0.28
     eslint
    0.28
    çłĶåĪ¶
    0.28
    æĹ¥å¤ľ
    0.28
    ayo
    0.27
    ysi
    0.27
    odial
    0.27
    Activations Density 1.210%

    No Known Activations