© 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. 31-TRANSCODER-HP
    7. 19661
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sigmoid
    -0.27
    è·¨è¶Ĭå¼ı
    -0.26
    æĢ¥éĢŁ
    -0.26
    ä¸įåģľåľ°
    -0.25
    æķħ
    -0.25
    -kind
    -0.24
    æºIJæºIJ
    -0.23
    .Class
    -0.23
    åIJijå¤ĸ
    -0.23
    -ground
    -0.23
    POSITIVE LOGITS
    äºĨå¤ļå°ij
    0.29
    é»İæĺİ
    0.26
    æľīå¤ļå°ij
    0.26
    å¦Ĥæŀľä¸įæĺ¯
    0.26
     sleeping
    0.25
    ipc
    0.25
    benh
    0.24
     Archive
    0.24
    resses
    0.24
    ä»Ģä¹ĪæŶåĢĻ
    0.24
    Activations Density 1.441%

    No Known Activations

    This feature has no known activations.