© 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. 20-TRANSCODER-HP
    7. 129006
    Prev
    Next
    INDEX
    Explanations

    orthopedics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æıIJåĩºçļĦ
    -0.28
    ä¿Ŀå®Ī
    -0.27
    è¶Ĭ
    -0.26
    容æĺĵ
    -0.25
     [[]
    -0.24
    æĮ½
    -0.24
    èĨ¨
    -0.24
     Ez
    -0.24
    ï¼ļ<
    -0.24
     jab
    -0.23
    POSITIVE LOGITS
    verty
    0.28
    欤
    0.28
    imately
    0.26
    craft
    0.26
    omes
    0.26
     essentially
    0.26
    ighb
    0.25
    paged
    0.25
    uctive
    0.25
    veal
    0.25
    Activations Density 4.752%

    No Known Activations