© 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. 131152
    Prev
    Next
    INDEX
    Explanations

    on

    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
    åı¸
    -0.28
    ä¸įå°ı
    -0.26
    comed
    -0.26
    ObjectContext
    -0.25
     lorem
    -0.25
    Solution
    -0.25
    avern
    -0.25
    -track
    -0.24
    çļĦå°±æĺ¯
    -0.24
    istics
    -0.24
    POSITIVE LOGITS
    æijĨåľ¨
    0.27
    碱
    0.25
     sola
    0.24
    æ°ijçĶŁ
    0.24
    ute
    0.23
    åıłåĬł
    0.23
    ä½İä»·
    0.23
    ali
    0.23
     Ply
    0.23
    itor
    0.23
    Activations Density 0.004%

    No Known Activations