© 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. 9-TRANSCODER-HP
    7. 30439
    Prev
    Next
    INDEX
    Explanations

    AEA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    laps
    -0.27
    æĸ°çīĪ
    -0.26
    meta
    -0.26
    ric
    -0.25
    iah
    -0.24
    大æķ°æį®
    -0.24
    anders
    -0.24
    ä¼
    -0.23
    åĴ³
    -0.23
     raj
    -0.23
    POSITIVE LOGITS
    å¼ķ
    0.28
    ä¸įæĪIJ
    0.28
     EÄŁ
    0.27
    anko
    0.27
     THEN
    0.26
    天天
    0.26
     Tow
    0.25
     Hughes
    0.25
    æİ¥
    0.25
     Howell
    0.24
    Activations Density 0.230%

    No Known Activations