© 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. 33-TRANSCODER-HP
    7. 52522
    Prev
    Next
    INDEX
    Explanations

    such

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    üc
    -0.27
    _NEXT
    -0.27
     UIControl
    -0.26
     Nack
    -0.26
    arro
    -0.26
     nextPage
    -0.25
     Provid
    -0.25
    ertest
    -0.24
    ,next
    -0.24
     citiz
    -0.24
    POSITIVE LOGITS
     such
    0.93
    è¿Ļæł·çļĦ
    0.85
    Such
    0.80
    such
    0.79
     Such
    0.79
     SUCH
    0.64
    éĢĻ樣çļĦ
    0.59
    æѤ类
    0.57
     ÑĤакое
    0.55
    è¿Ļæł·ä¸Ģ个
    0.54
    Activations Density 0.014%

    No Known Activations