© 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. 32-TRANSCODER-HP
    7. 44003
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸İåħ¶ä»ĸ
    -0.26
    峡
    -0.25
    åºĶ该
    -0.25
    è¤Ĭ
    -0.24
    uplic
    -0.24
    ä¹ŁåºĶ该
    -0.24
     cameo
    -0.24
    æĶ¯çº¿
    -0.24
    lettes
    -0.24
    ä¸įåIJĮçļĦ
    -0.23
    POSITIVE LOGITS
     wh
    0.40
     first
    0.39
     thus
    0.36
     as
    0.35
     e
    0.32
     all
    0.32
    wh
    0.32
    ?-
    0.31
     similarly
    0.31
     universally
    0.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.