© 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. 52662
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ,[],
    -0.25
    eria
    -0.25
     Destination
    -0.24
    GridColumn
    -0.24
    éĹŃçݯ
    -0.24
    tings
    -0.24
    ISTR
    -0.24
    "){
    -0.24
    пп
    -0.24
     Jail
    -0.23
    POSITIVE LOGITS
    æķ¢äºİ
    0.26
    æ¯į
    0.26
    -da
    0.26
    ãĥ¬ãĥ¼
    0.25
    æĥ³è±¡åĬĽ
    0.25
    ductor
    0.24
    è¾ĥé«ĺ
    0.24
    à¹īา
    0.24
     ÑĢаÑģÑģмаÑĤ
    0.24
    plorer
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.