© 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. 27-TRANSCODER-HP
    7. 9773
    Prev
    Next
    INDEX
    Explanations

    worst

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    implicit
    -0.26
    -TV
    -0.26
    Ãłn
    -0.26
    zá
    -0.24
    -top
    -0.24
    trinsic
    -0.24
    æĢ»çļĦ
    -0.24
    andid
    -0.24
    åįģ足
    -0.24
    æīĢèĩ´
    -0.24
    POSITIVE LOGITS
     capable
    0.28
    s
    0.27
    -case
    0.26
    days
    0.26
    LEASE
    0.24
    ä½ļ
    0.24
    éĢĤ度
    0.23
    ed
    0.23
    骸
    0.23
    ogne
    0.23
    Activations Density 0.850%

    No Known Activations