© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8109
    Prev
    Next
    INDEX
    Explanations

    Informational/News articles

    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
    знаÑĩ
    -0.29
    æĺ¯æĮĩ
    -0.28
    ä½ľä¸ºä¸Ģç§į
    -0.28
    å±Ģéķ¿
    -0.27
    åĪĴ
    -0.26
    ä¸įæĺ¯ä¸Ģ个
    -0.26
    ä¸įæĺ¯
    -0.26
    sure
    -0.26
    æĮĩçļĦæĺ¯
    -0.26
     meaning
    -0.25
    POSITIVE LOGITS
    ($__
    0.32
    iev
    0.29
    loff
    0.27
    cki
    0.27
    enso
    0.25
     matters
    0.24
     Sponsored
    0.24
     SOLD
    0.24
     hoodie
    0.24
    arie
    0.24
    Activations Density 0.058%

    No Known Activations