© 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. 88930
    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
    移
    -0.29
    çĻ½ç³ĸ
    -0.25
    tests
    -0.25
    ectl
    -0.24
    -tests
    -0.24
    âĦ
    -0.24
    è¯ķéªĮ
    -0.24
     immune
    -0.24
    .shift
    -0.24
    леÑĢ
    -0.23
    POSITIVE LOGITS
    .onclick
    0.25
    èĬ·
    0.25
    UTH
    0.23
     seeded
    0.23
     clicked
    0.23
     hockey
    0.23
    .azure
    0.23
    ĵį
    0.23
    mounted
    0.23
    (cond
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.