© 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. 18-TRANSCODER-HP
    7. 90081
    Prev
    Next
    INDEX
    Explanations

    Information retrieval texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĶ¾å¼ĥäºĨ
    -0.28
    ä¸»å¼ł
    -0.28
    ilon
    -0.28
    ÑĤан
    -0.27
     emphas
    -0.27
    è¿Ļ两年
    -0.27
    强è°ĥ
    -0.25
    æĹ¥èµ·
    -0.25
     Disclaimer
    -0.25
    adv
    -0.24
    POSITIVE LOGITS
    icode
    0.29
    ä¸ŃåĽ½æĶ¿åºľ
    0.28
    ONY
    0.25
    iser
    0.25
    è£Ĥ
    0.24
    骨头
    0.24
     GENERATED
    0.24
    неÑĢ
    0.23
    _DM
    0.23
    æłī
    0.23
    Activations Density 14.397%

    No Known Activations