© 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. 129044
    Prev
    Next
    INDEX
    Explanations

    websites and software

    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
    Furthermore
    -0.28
    并äºİ
    -0.28
    å¹¶åľ¨
    -0.28
    ideo
    -0.27
     Moreover
    -0.27
    Moreover
    -0.27
    iners
    -0.27
     Furthermore
    -0.26
    åĨįåĬłä¸Ĭ
    -0.26
    è¿ĺè¦ģ
    -0.26
    POSITIVE LOGITS
    :bg
    0.24
    ooth
    0.24
    ạng
    0.23
    mitt
    0.23
    è¡·
    0.23
    å¤ļæĸ¹
    0.23
    зд
    0.23
     Extr
    0.23
    éĽĨåĽ¢
    0.23
    åĢ¾
    0.23
    Activations Density 0.036%

    No Known Activations