© 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. 39604
    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
    Negative Logits
    æ½ľ
    -0.28
    eler
    -0.28
    uffle
    -0.26
    çªĥ
    -0.25
    elen
    -0.24
    alue
    -0.24
    å®ŀ
    -0.24
    çŁ¾
    -0.23
    eration
    -0.23
    elter
    -0.23
    POSITIVE LOGITS
    gap
    0.24
     powering
    0.24
    gL
    0.24
    :";č↵
    0.23
    é¹į
    0.23
    >;č↵
    0.23
    enaries
    0.23
    inders
    0.23
    线æĿ¡
    0.23
    OrNil
    0.23
    Activations Density 0.682%

    No Known Activations

    This feature has no known activations.