© 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. 7751
    Prev
    Next
    INDEX
    Explanations

    virtualization and computers

    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
    ลาà¸Ķ
    -0.28
    è¯į
    -0.27
    éĶµ
    -0.24
    ä¸įè¦ģ太
    -0.24
    äch
    -0.24
    人éĻħ
    -0.24
    ä¸įæ¸ħæ¥ļ
    -0.24
     mary
    -0.24
    è©ŀ
    -0.23
     ech
    -0.23
    POSITIVE LOGITS
    æĺ¯ä¸Ģ座
    0.27
    tru
    0.27
    绣
    0.27
    swer
    0.26
    绣ä¸Ģ
    0.26
     pinned
    0.26
    éĥ¢
    0.26
    BB
    0.25
    èµı
    0.25
     gratuitement
    0.25
    Activations Density 0.020%

    No Known Activations