© 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. 41546
    Prev
    Next
    INDEX
    Explanations

    Web addresses

    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
     mapDispatchToProps
    -0.26
    plier
    -0.25
    elial
    -0.25
    åķ®
    -0.24
    ä¸įæĺĵ
    -0.24
    olia
    -0.24
    éĽħ
    -0.23
    åĮĸè¿Ľç¨ĭ
    -0.23
    -awesome
    -0.23
    -spot
    -0.23
    POSITIVE LOGITS
    以åIJİ
    0.28
    以å¾Į
    0.27
    æĮ½
    0.26
    rending
    0.26
     使çĶ¨
    0.25
     ...↵
    0.25
    çĹ£
    0.25
    ster
    0.25
     usage
    0.24
     Usage
    0.24
    Activations Density 1.679%

    No Known Activations