© 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. 142474
    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
     chances
    -0.28
     acceptance
    -0.26
    tm
    -0.25
    inis
    -0.25
    world
    -0.25
     Model
    -0.24
    ipp
    -0.24
    omatic
    -0.24
     model
    -0.24
    缮çļĦæĺ¯
    -0.23
    POSITIVE LOGITS
    igte
    0.28
     grav
    0.27
    åĵįåºĶ
    0.26
    æ©Ħ
    0.26
    æģ°æģ°
    0.25
    igy
    0.25
    IJľ
    0.25
    chè
    0.25
    ä»Ģä¹Īæł·çļĦ
    0.25
    è°ĥåij³
    0.25
    Activations Density 21.297%

    No Known Activations

    This feature has no known activations.