© 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. 35-TRANSCODER-HP
    7. 40560
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -Ray
    -0.26
    NG
    -0.24
    æĶ¹åĪ¶
    -0.24
    åħ¹
    -0.23
     outnumber
    -0.23
    hiro
    -0.23
     turnaround
    -0.22
     ÑĤÑĢÑĥд
    -0.22
    æľīå¤ļ大
    -0.22
    æķ´é½IJ
    -0.22
    POSITIVE LOGITS
    ibu
    0.26
    ousel
    0.25
    á»Ŀ
    0.25
    iera
    0.24
    icing
    0.24
     apologies
    0.24
    ặc
    0.24
    dden
    0.23
    omat
    0.23
    opl
    0.23
    Activations Density 14.035%

    No Known Activations

    This feature has no known activations.