© 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. 56335
    Prev
    Next
    INDEX
    Explanations

    late 1800s

    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
    ä¸įèµ·
    -0.28
    åħĪ
    -0.26
    ograms
    -0.26
    {}
    -0.25
    è¿ŀç»Ń
    -0.25
     alf
    -0.24
    æĽ·
    -0.24
    éĢ£çºĮ
    -0.24
    çģ¼
    -0.23
    alf
    -0.23
    POSITIVE LOGITS
    ogne
    0.27
    qid
    0.26
    鸦
    0.26
    å·¥ä¸ļåĮĸ
    0.26
    åľ°éģĵ
    0.26
    å±ħ
    0.26
    .Stage
    0.25
    éĴŁ
    0.25
    大è¡Ĺ
    0.24
    iola
    0.24
    Activations Density 0.001%

    No Known Activations