© 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. 39763
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĿĻ
    -0.26
    ROTO
    -0.26
    arkan
    -0.26
    mana
    -0.25
    erior
    -0.25
    undance
    -0.24
    .Args
    -0.24
    enta
    -0.24
    enz
    -0.23
     financ
    -0.23
    POSITIVE LOGITS
    insky
    0.26
    ève
    0.25
     impunity
    0.25
     sant
    0.24
    åįĬ导
    0.24
     stronÄĻ
    0.24
    /yyyy
    0.24
    ë¦ĩ
    0.23
     Monterey
    0.23
    kah
    0.23
    Activations Density 0.460%

    No Known Activations

    This feature has no known activations.