© 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. 9586
    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
    æī¿
    -0.26
    ç»ıèIJ¥æ´»åĬ¨
    -0.26
    å·¥ç¨ĭå¸Ī
    -0.26
    èĤ¡ç¥¨
    -0.25
    -sk
    -0.24
     eens
    -0.24
    åİĨæŶ
    -0.24
    -intensive
    -0.24
     Off
    -0.24
     =
    -0.24
    POSITIVE LOGITS
    å¬ĸ
    0.27
    .percent
    0.26
    iclass
    0.26
     '<%=
    0.26
    棨
    0.25
    çŃīåĢĻ
    0.25
    ä½Ķ
    0.24
    /group
    0.24
     Prozent
    0.24
    æī®
    0.23
    Activations Density 2.376%

    No Known Activations

    This feature has no known activations.