© 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. 54625
    Prev
    Next
    INDEX
    Explanations

    coding and technical language

    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
     Ted
    -0.28
     if
    -0.28
    cheng
    -0.28
     nếu
    -0.26
    å¦Ĥæŀľæĺ¯
    -0.25
    å¦ĤæŀľæĪij们
    -0.25
    大家éĥ½åľ¨
    -0.25
    æĪijè¦ģ
    -0.25
    æļĦ
    -0.25
     Whoever
    -0.25
    POSITIVE LOGITS
    åĨ°
    0.27
    icias
    0.27
    -UA
    0.27
     anchored
    0.25
    forge
    0.25
    iland
    0.25
    åĪĨç±»
    0.24
     classify
    0.24
    iore
    0.24
    姿
    0.24
    Activations Density 0.013%

    No Known Activations