© 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. 106947
    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
     otherwise
    -0.29
     imp
    -0.29
     co
    -0.28
     sup
    -0.28
     never
    -0.27
     already
    -0.27
     moments
    -0.27
     inf
    -0.26
     dis
    -0.26
     moment
    -0.26
    POSITIVE LOGITS
     Organizer
    0.27
     Relations
    0.26
     Rising
    0.26
     Reporter
    0.26
     Entries
    0.26
     Lad
    0.25
     Shoot
    0.25
    stown
    0.25
     Recognition
    0.25
     Witnesses
    0.25
    Activations Density 1.030%

    No Known Activations

    This feature has no known activations.