© 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. 41722
    Prev
    Next
    INDEX
    Explanations

    Text fragments/excerpts

    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
    ieg
    -0.31
    .nt
    -0.29
    igin
    -0.29
    ório
    -0.28
    次ä¼ļè®®
    -0.27
    Pow
    -0.27
    oria
    -0.27
    ãģĤãģ£ãģ¦
    -0.27
    tern
    -0.26
    pow
    -0.26
    POSITIVE LOGITS
     //!<
    0.27
    (Constructor
    0.26
    .Tx
    0.26
    å¾®åķĨ
    0.25
     tread
    0.25
    ATER
    0.25
    .getOutputStream
    0.24
    é¦ĸ缸
    0.24
     unmist
    0.24
     Hazard
    0.24
    Activations Density 0.124%

    No Known Activations