© 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. 149331
    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
     yourselves
    -0.30
    stay
    -0.29
    ån
    -0.27
    OLA
    -0.27
     ------>
    -0.26
    remain
    -0.26
    iguiente
    -0.26
    aminer
    -0.26
    ampion
    -0.25
    emente
    -0.25
    POSITIVE LOGITS
    æ¼Ķ示
    0.27
    #ad
    0.27
    æĮ«
    0.27
    éķĬ
    0.26
    人éĥ½
    0.26
    åĵĦ
    0.26
    祸
    0.24
     procur
    0.24
    çļĦ人æĿ¥è¯´
    0.24
     dil
    0.24
    Activations Density 0.120%

    No Known Activations

    This feature has no known activations.