© 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. 22-TRANSCODER-HP
    7. 113121
    Prev
    Next
    INDEX
    Explanations

    ak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸į说
    -0.30
    AUSE
    -0.28
    éĤ£ä¸ĢåĪ»
    -0.26
    Pinterest
    -0.26
     [+
    -0.26
    ãĥªãĤ¹ãĤ¯
    -0.25
    olon
    -0.24
    æĪijä¼ļ
    -0.24
    urator
    -0.23
     Assass
    -0.23
    POSITIVE LOGITS
    çļĦæĥħ
    0.25
    ott
    0.25
    lib
    0.23
    åİĭ
    0.23
    jak
    0.23
    l
    0.23
    è¾¹
    0.23
     surprised
    0.23
    -ul
    0.23
    w
    0.22
    Activations Density 0.002%

    No Known Activations