© 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. 19-TRANSCODER-HP
    7. 9608
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ito
    -0.28
    .places
    -0.27
    rites
    -0.26
    CUR
    -0.26
    Acceler
    -0.24
    ativo
    -0.24
    -cur
    -0.23
    .rcParams
    -0.23
    y
    -0.23
     target
    -0.23
    POSITIVE LOGITS
    :hidden
    0.31
    emachine
    0.27
    æµģåĬ¨æĢ§
    0.26
    åĢĴ
    0.26
    æŃ£æĺ¯åĽłä¸º
    0.25
    uden
    0.24
    æŃ·åı²
    0.23
    买车
    0.23
    ç§ĺå¯Ĩ
    0.23
    =size
    0.23
    Activations Density 0.152%

    No Known Activations

    This feature has no known activations.