© 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. 39631
    Prev
    Next
    INDEX
    Explanations

    altern

    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
    ä¸İåIJ¦
    -0.29
     Cust
    -0.28
     haz
    -0.28
    åĸīåĴĻ
    -0.25
     dys
    -0.25
    forth
    -0.25
     dumping
    -0.25
    leh
    -0.25
     fat
    -0.24
     provinc
    -0.24
    POSITIVE LOGITS
    sis
    0.29
    sitemap
    0.26
    nia
    0.25
    ropri
    0.25
    Lng
    0.25
    nic
    0.25
    sic
    0.25
    çľĭä¸Ģçľĭ
    0.25
    æĺ¥å¤ı
    0.25
    ãģªãģĦãĤĪãģĨãģ«
    0.24
    Activations Density 0.210%

    No Known Activations