© 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. 22-TRANSCODER-HP
    7. 110921
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    acon
    -0.27
    atical
    -0.25
    agr
    -0.24
     hints
    -0.24
     Mission
    -0.24
    hint
    -0.24
    èĬ±
    -0.24
    ("---
    -0.24
     clustering
    -0.24
     Midlands
    -0.23
    POSITIVE LOGITS
     sorts
    0.26
    æ±ģ
    0.25
    举
    0.24
    娩
    0.24
    ily
    0.24
    моÑĢ
    0.23
     sorte
    0.23
     GlobalKey
    0.23
    oplast
    0.23
    0.23
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.