© 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. 131036
    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
     iris
    -0.27
    éķ¿å¤§
    -0.26
    atab
    -0.25
    åĴĮ个人
    -0.25
    anova
    -0.24
     imp
    -0.24
    èĩªçĦ¶ç§ijåѦ
    -0.24
    åIJĪä¸Ģ
    -0.23
     ÑģамоÑģÑĤоÑıÑĤелÑĮно
    -0.23
    çļĦçŃĶæ¡Ī
    -0.23
    POSITIVE LOGITS
    theless
    0.27
    æĹłçĸijæĺ¯
    0.26
     Finn
    0.26
    opard
    0.26
     FALL
    0.25
    æĦ¿
    0.25
    é¡ĺ
    0.24
     Draws
    0.24
    ämp
    0.24
     fest
    0.23
    Activations Density 8.651%

    No Known Activations

    This feature has no known activations.