© 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. 112982
    Prev
    Next
    INDEX
    Explanations

    Mixed text data

    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
    efined
    -0.26
    çļĦä¼łç»Ł
    -0.25
    ä¿Ŀå§Ĩ
    -0.25
    ult
    -0.24
    Shown
    -0.24
    clipboard
    -0.24
    venture
    -0.24
    okit
    -0.23
    çļĦä½ľåĵģ
    -0.23
    -reviewed
    -0.23
    POSITIVE LOGITS
    iges
    0.27
    姿
    0.26
    JO
    0.26
    欢è¿İ
    0.25
    åģıå·®
    0.25
    积åĪĨ
    0.25
    ayo
    0.24
     Rivers
    0.24
    .RES
    0.24
    å¹²æī°
    0.24
    Activations Density 0.002%

    No Known Activations