© 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. 19-TRANSCODER-HP
    7. 9543
    Prev
    Next
    INDEX
    Explanations

    Blog post / article text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĪijè¦ģ
    -0.28
    主ä½ĵ责任
    -0.27
     Human
    -0.26
     meta
    -0.26
    noc
    -0.25
    phas
    -0.25
     Fare
    -0.25
    .pi
    -0.25
     sche
    -0.25
    meta
    -0.24
    POSITIVE LOGITS
    ä¼łéĹ»
    0.33
    ä¼łè¨Ģ
    0.33
    å½ĵåľ°äºº
    0.33
    ä¸įå®ļ
    0.32
    åħ¬è®¤çļĦ
    0.31
    人们
    0.29
     affair
    0.29
     gossip
    0.28
    IELD
    0.28
    é£İæ°Ķ
    0.28
    Activations Density 0.080%

    No Known Activations