© 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. 39411
    Prev
    Next
    INDEX
    Explanations

    shapes

    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
    磼
    -0.30
    游æĪı
    -0.27
    æĦıåIJij
    -0.26
    æij
    -0.25
    æĦŁè§ī
    -0.25
    plusplus
    -0.25
    iller
    -0.24
    mé
    -0.23
     pip
    -0.23
     sar
    -0.23
    POSITIVE LOGITS
    èĢĥ
    0.26
    -thumbnail
    0.26
    Incoming
    0.26
    Case
    0.26
     Wax
    0.26
    è¦Ĩ
    0.25
    æ½¢
    0.25
    è´¬åĢ¼
    0.25
    Fact
    0.25
    .Hosting
    0.25
    Activations Density 0.251%

    No Known Activations