© 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. 9316
    Prev
    Next
    INDEX
    Explanations

    including

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĻ«
    -0.25
    åĻ¤
    -0.25
    æīī
    -0.24
    pur
    -0.24
    .look
    -0.24
    зон
    -0.24
     Assassin
    -0.24
     Brigade
    -0.24
    Feels
    -0.23
     Mechan
    -0.23
    POSITIVE LOGITS
    oks
    0.29
    DEX
    0.27
    puted
    0.26
    åĪ°è¾¾
    0.25
     chalk
    0.25
    kea
    0.24
    ä½Ĩä¸įéĻIJäºİ
    0.24
    .PO
    0.23
    pear
    0.23
     NU
    0.23
    Activations Density 0.162%

    No Known Activations