© 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. 151266
    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
     listing
    -0.27
    port
    -0.27
     shortcut
    -0.25
    EM
    -0.25
    pons
    -0.25
    ists
    -0.24
    ogui
    -0.24
    æ³¥
    -0.24
     Listing
    -0.24
    pon
    -0.24
    POSITIVE LOGITS
    åĭº
    0.25
    æĪĺ
    0.25
     sprung
    0.24
    ä¼Ĺ
    0.23
    ç¿¥
    0.23
    YPES
    0.23
    entionPolicy
    0.23
    енн
    0.23
    zych
    0.23
    æIJĶ
    0.22
    Activations Density 1.271%

    No Known Activations

    This feature has no known activations.