© 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. 20-TRANSCODER-HP
    7. 62698
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    滾
    -0.31
    ABCDE
    -0.31
    ince
    -0.29
    æ»ļ
    -0.29
    çĸijéļ¾
    -0.26
     cb
    -0.26
    头èĦij
    -0.26
    ç£Ļ
    -0.25
    CB
    -0.25
     пÑĢедмеÑĤ
    -0.25
    POSITIVE LOGITS
    idal
    0.27
    ä¸ĢéĿ¢
    0.25
    èĦ¸
    0.25
    }*/↵↵
    0.24
    conto
    0.24
     emitting
    0.24
    izin
    0.23
    ãģĭãģª
    0.23
     envisioned
    0.23
    UMAN
    0.23
    Activations Density 0.977%

    No Known Activations

    This feature has no known activations.