© 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. 9657
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    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
    ä¸ĢçĤ¹
    -0.29
    ordable
    -0.27
    âĢ¦”↵↵
    -0.27
    éķĤ
    -0.26
     Pens
    -0.26
    è¾¹ç¼ĺ
    -0.26
    ä¸į说
    -0.26
    |string
    -0.25
    ä¸įå°½
    -0.25
    foil
    -0.25
    POSITIVE LOGITS
    /topic
    0.29
     main
    0.27
    laÅŁ
    0.26
    ublish
    0.25
    main
    0.24
    GLE
    0.24
    âŀĶ
    0.24
    YA
    0.24
    isnan
    0.23
    gcc
    0.23
    Activations Density 0.015%

    No Known Activations