© 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. 24-TRANSCODER-HP
    7. 151447
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    zy
    -0.28
    ony
    -0.27
    èĪ¬
    -0.27
    çģ¯
    -0.26
    éĵľ
    -0.26
    enant
    -0.26
    еж
    -0.26
    pon
    -0.25
    utory
    -0.25
    FREE
    -0.25
    POSITIVE LOGITS
    çļĦçłĶ究
    0.26
    çłĶ究æĪIJæŀľ
    0.26
    æīĢ说çļĦ
    0.26
    ï¼ģ↵↵↵↵
    0.25
    ç´ĢéĮĦ
    0.25
    è®°è½½
    0.25
    equip
    0.25
     recorded
    0.25
     shave
    0.25
    çłĶ究æĬ¥åijĬ
    0.25
    Activations Density 0.057%

    No Known Activations

    This feature has no known activations.