© 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. 142432
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ischer
    -0.32
    æľīæľŁ
    -0.28
    erd
    -0.27
     salir
    -0.26
     [+
    -0.25
    èѬå¦Ĥ
    -0.25
    代表
    -0.25
    迹
    -0.25
     alternating
    -0.24
     assignable
    -0.24
    POSITIVE LOGITS
     ourselves
    0.29
    è
    0.28
     herself
    0.28
     itself
    0.27
    æĺ¯ä¸Ģ座
    0.27
     themselves
    0.27
    LETE
    0.26
    æľ¬äºº
    0.25
    ensions
    0.25
    å¦Ĥæľīä¾µæĿĥ
    0.25
    Activations Density 0.778%

    No Known Activations

    This feature has no known activations.