© 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. 14-TRANSCODER-HP
    7. 39443
    Prev
    Next
    INDEX
    Explanations

    Mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Murdoch
    -0.28
    å¸ļ
    -0.28
     wheels
    -0.27
    éļıæīĭ
    -0.27
    æ³Ľ
    -0.26
    èĩªçIJĨ
    -0.26
    enson
    -0.26
    athan
    -0.25
    ĪæĿĥ
    -0.25
    Corn
    -0.25
    POSITIVE LOGITS
     Symbols
    0.27
    iphy
    0.26
     Natur
    0.26
    ç»ĦæĪIJçļĦ
    0.25
    pir
    0.25
    _RA
    0.25
    IPS
    0.25
    pv
    0.25
    Players
    0.24
     Compet
    0.24
    Activations Density 0.134%

    No Known Activations