© 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. 39488
    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
    isses
    -0.26
    angelog
    -0.26
    mma
    -0.26
    locked
    -0.25
    prime
    -0.25
    Private
    -0.25
    nr
    -0.25
     Xxx
    -0.24
    aton
    -0.24
    说æĺİ书
    -0.24
    POSITIVE LOGITS
    ä¾ĭå¤ĸ
    0.31
    çªĦ
    0.27
    ients
    0.26
     torso
    0.26
    åݿ级
    0.25
     relied
    0.25
    cies
    0.25
    олж
    0.25
    olith
    0.25
    Ñĭми
    0.25
    Activations Density 1.581%

    No Known Activations

    This feature has no known activations.