© 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. 64531
    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
    suit
    -0.30
    lescope
    -0.29
    conc
    -0.25
    isan
    -0.25
    ÑĨе
    -0.24
     `,
    -0.24
     Dispatch
    -0.24
    西äºļ
    -0.23
     Conc
    -0.23
     unless
    -0.23
    POSITIVE LOGITS
    çĶ·äºº
    0.28
     kep
    0.27
    anja
    0.26
    为空
    0.25
    ä¸įä¹ı
    0.25
    /interfaces
    0.25
    ellas
    0.24
    å¿Ļç¢Į
    0.24
    ä¼IJ
    0.24
    åĥıæĺ¯
    0.24
    Activations Density 8.715%

    No Known Activations

    This feature has no known activations.