© 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. 130986
    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
    Ä°Z
    -0.31
    äºĭä¸ļåıijå±ķ
    -0.26
     lowercase
    -0.25
    osaur
    -0.25
    oda
    -0.24
    æī¹åĩĨ
    -0.24
    izens
    -0.24
    çľģåħ¬å®īåİħ
    -0.23
    èݺ
    -0.23
     α
    -0.23
    POSITIVE LOGITS
    姿æĢģ
    0.27
     Strike
    0.25
    è¡Ķ
    0.24
    اة
    0.24
    éĻIJ
    0.24
     '=',
    0.24
    åľ°çľĭçĿĢ
    0.24
     strikes
    0.24
    èµĤ
    0.24
    éĻIJæŶ
    0.24
    Activations Density 67.110%

    No Known Activations

    This feature has no known activations.