© 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. 130867
    Prev
    Next
    INDEX
    Explanations

    Punctuation in diverse texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æľīä¸ĢçĤ¹
    -0.32
     Oprah
    -0.30
    æīĢæıIJä¾ĽçļĦ
    -0.27
    æīĢæıIJä¾Ľ
    -0.26
     sunk
    -0.25
    JV
    -0.25
    rus
    -0.25
     Casc
    -0.25
    rant
    -0.24
     admitted
    -0.24
    POSITIVE LOGITS
    inya
    0.31
    离
    0.28
    ellant
    0.25
    _engine
    0.25
     incons
    0.24
    æł¹
    0.23
    alez
    0.23
    istrate
    0.23
    .raise
    0.23
    项
    0.23
    Activations Density 18.661%

    No Known Activations