© 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. 129145
    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
     implication
    -0.28
    olem
    -0.25
    iphy
    -0.25
    ä¸ĬéĻIJ
    -0.25
     Barber
    -0.25
     Boundary
    -0.25
    便åı¯
    -0.24
    ewitness
    -0.24
    æݥ管
    -0.24
     fundament
    -0.24
    POSITIVE LOGITS
    æĮŁ
    0.28
    积累äºĨ
    0.26
    CEF
    0.26
    ardy
    0.26
    æĮª
    0.26
    æIJģ
    0.25
     locations
    0.25
    CMS
    0.25
     dumping
    0.24
    gram
    0.24
    Activations Density 1.344%

    No Known Activations

    This feature has no known activations.