© 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. 62607
    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
    åħħå®ŀ
    -0.30
    otts
    -0.28
    -bed
    -0.27
    ä¸ĢæĬĬ
    -0.27
    bed
    -0.25
     Essentially
    -0.25
    illum
    -0.25
    èī¯
    -0.25
     states
    -0.24
    omba
    -0.24
    POSITIVE LOGITS
    izador
    0.27
    RuleContext
    0.26
    ä¸Ģè¾ĪåŃIJ
    0.25
    á»ĩu
    0.25
    ä½ĵçİ°
    0.25
    æľ¬ç½ij
    0.24
     демо
    0.24
     Values
    0.24
    åħ¬å¸ĥçļĦ
    0.24
     validating
    0.23
    Activations Density 79.091%

    No Known Activations

    This feature has no known activations.