© 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. 108680
    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
    ioc
    -0.32
    交æį¢
    -0.28
    swith
    -0.27
    capt
    -0.27
    iu
    -0.26
    Recognition
    -0.26
    åıįåĵį
    -0.26
     opening
    -0.25
    [#
    -0.24
     collaborate
    -0.24
    POSITIVE LOGITS
    istine
    0.26
    eros
    0.26
    çļĦçIJĨæĥ³
    0.25
    çĤ¹äºĨ
    0.25
    èĵ¬åĭĥ
    0.25
    æĪĸå¤ļæĪĸå°ij
    0.25
    让æĤ¨
    0.24
    è¿ĻåĦ¿
    0.24
    åıijåŀĭ
    0.24
    adal
    0.24
    Activations Density 87.898%

    No Known Activations

    This feature has no known activations.