© 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. 25-TRANSCODER-HP
    7. 107092
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iming
    -0.28
     diss
    -0.26
    aldi
    -0.26
     effectively
    -0.26
     rou
    -0.26
     odd
    -0.26
     Odd
    -0.26
    说ä»Ģä¹Ī
    -0.26
    ën
    -0.25
    åĵªéĩĮ
    -0.25
    POSITIVE LOGITS
    conv
    0.27
    educ
    0.26
    setting
    0.26
    çĭ¬ç«ĭèij£äºĭ
    0.25
    structures
    0.24
     Beans
    0.24
    cars
    0.24
    è¿Ļæł·ä¸Ģ个
    0.23
    çIJĨåıij
    0.23
    struct
    0.23
    Activations Density 0.479%

    No Known Activations

    This feature has no known activations.