© 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. 9529
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
     historically
    -0.38
    åİĨæĿ¥
    -0.36
     traditionally
    -0.36
    åİĨåı²æĤłä¹ħ
    -0.35
    çļĦä¼łç»Ł
    -0.33
     tradition
    -0.33
    çļĦä¹łæĥ¯
    -0.33
     Trad
    -0.33
    å¤ļå¹´æĿ¥
    -0.33
    å¤ļå¹´
    -0.32
    POSITIVE LOGITS
    沿éĢĶ
    0.27
    åĪ°å¤Ħ
    0.26
    ents
    0.25
     fals
    0.24
    icipants
    0.24
    伪è£ħ
    0.24
    åĽĽå¤Ħ
    0.24
    éĹ³
    0.23
    .pass
    0.23
     _
    0.23
    Activations Density 0.258%

    No Known Activations