© 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. 27-TRANSCODER-HP
    7. 7818
    Prev
    Next
    INDEX
    Explanations

    accounting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Economic
    -0.31
     economic
    -0.28
    ç»ıæµİ
    -0.27
     economy
    -0.27
    åķ¬
    -0.27
    economic
    -0.26
     Bew
    -0.25
     Economy
    -0.25
    .Constant
    -0.25
    aine
    -0.24
    POSITIVE LOGITS
    éģµ
    0.31
    icated
    0.28
    ascript
    0.27
    elsey
    0.27
    .press
    0.26
    town
    0.26
    leta
    0.25
    åijĻ
    0.24
     Sheriff
    0.24
    .writeln
    0.24
    Activations Density 0.006%

    No Known Activations