© 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. 142510
    Prev
    Next
    INDEX
    Explanations

    Excerpts from longer 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
    Negative Logits
    å¡Į
    -0.32
    @[
    -0.27
    å±ħæ°ij
    -0.26
    ográf
    -0.26
    èĢĮæĪIJ
    -0.25
     fark
    -0.23
    åĢ¾åIJ¬
    -0.23
    å§ĭäºİ
    -0.23
    åĨ³å¿ĥ
    -0.23
    è¨ĺ
    -0.23
    POSITIVE LOGITS
     lighter
    0.26
    xE
    0.25
    obao
    0.24
    rint
    0.24
    (coder
    0.24
     unlocked
    0.24
    usat
    0.24
    è¯Ńæĸĩ
    0.24
    éĴŀ
    0.23
     lender
    0.23
    Activations Density 1.121%

    No Known Activations