© 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. 27-TRANSCODER-HP
    7. 9916
    Prev
    Next
    INDEX
    Explanations

    Biology/Nature articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ìĤ°
    -0.28
     b
    -0.27
    鬻
    -0.26
     juven
    -0.24
    åħļçļĦ建设
    -0.24
    æĸIJ
    -0.24
     Old
    -0.24
     Hard
    -0.24
     hard
    -0.24
     stretches
    -0.24
    POSITIVE LOGITS
    {}{↵
    0.27
    éĹ¨æ§Ľ
    0.27
    desk
    0.27
     }</
    0.27
    []{"
    0.25
    encent
    0.24
    {id
    0.24
    icrosoft
    0.24
    第ä¸īæĸ¹
    0.24
    ä¸īæĸ¹
    0.24
    Activations Density 0.005%

    No Known Activations