© 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. 20-TRANSCODER-HP
    7. 130970
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    eselect
    -0.27
    [out
    -0.27
    lingen
    -0.27
    ä¸ªé¡¹çĽ®
    -0.25
    æ¯ķä¸ļåIJİ
    -0.24
     unl
    -0.24
    è°ĵ
    -0.24
    å²ģ以ä¸Ĭ
    -0.24
     Pru
    -0.23
    è¬Ĥ
    -0.23
    POSITIVE LOGITS
     shakes
    0.27
    å¾ģæ±ĤæĦıè§ģ
    0.27
    PEC
    0.26
     sliding
    0.26
    REGION
    0.25
    yr
    0.25
    èħ¥
    0.24
     celebrations
    0.24
     curb
    0.24
    омеÑĢ
    0.24
    Activations Density 20.876%

    No Known Activations

    This feature has no known activations.