© 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. 113163
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     cricket
    -0.28
    osp
    -0.24
    æī©
    -0.24
    åIJĪ
    -0.23
     oscill
    -0.23
    æĵ´
    -0.23
     hormone
    -0.23
    reur
    -0.23
    emic
    -0.23
     different
    -0.22
    POSITIVE LOGITS
    è¶Ĭ好
    0.28
    èµ¢å¾Ĺ
    0.27
     trails
    0.26
    è¶Ĭæĺ¯
    0.26
    ä¸Ģä¼ļ
    0.26
    åĩ¡æĺ¯
    0.26
    quires
    0.26
    æģĥ
    0.26
    æľĢå¿«
    0.25
    åģļçļĦäºĭ
    0.25
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.