© 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. 113156
    Prev
    Next
    INDEX
    Explanations

    general text

    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
    ponsor
    -0.25
    çĦ
    -0.25
     expans
    -0.24
    鸳
    -0.24
    æ·±åĪ»çļĦ
    -0.23
     inval
    -0.23
     setC
    -0.23
     uniform
    -0.23
     rigorous
    -0.23
     Tâm
    -0.23
    POSITIVE LOGITS
     briefly
    0.62
    å°ijéĩı
    0.58
    çŁŃæļĤ
    0.54
    å°ij许
    0.54
     slightly
    0.51
     slight
    0.50
    èĩ³å°ij
    0.47
     momentarily
    0.47
    æļĤæŶ
    0.46
    ç¨įå¾®
    0.46
    Activations Density 0.002%

    No Known Activations