© 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. 19-TRANSCODER-HP
    7. 9446
    Prev
    Next
    INDEX
    Explanations

    Start of documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¾Ī满æĦı
    -0.28
    queryString
    -0.27
     civ
    -0.26
    çŃĶåºĶ
    -0.25
    满æĦı
    -0.25
    çı¥
    -0.24
     Jain
    -0.24
    civil
    -0.24
     Civil
    -0.24
    mine
    -0.23
    POSITIVE LOGITS
    lotte
    0.28
    è¿ĩ大
    0.28
    éĹ²
    0.27
    æĿ¯
    0.26
    è§Ĩéĩİ
    0.26
    åIJĪãģĦ
    0.26
    itra
    0.26
    ç²Ĺ
    0.26
    fas
    0.24
    harga
    0.24
    Activations Density 0.008%

    No Known Activations