© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7228
    Prev
    Next
    INDEX
    Explanations

    Titles and positions

    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
    emade
    -0.27
    raise
    -0.27
     tallest
    -0.26
    elin
    -0.26
    ESS
    -0.25
    ubby
    -0.25
     Dough
    -0.24
     Spike
    -0.24
    pth
    -0.24
     cheapest
    -0.24
    POSITIVE LOGITS
    æľīåĵªäºĽ
    0.26
    æĢ§å¼º
    0.25
    åľĥ
    0.24
     defined
    0.24
    ism
    0.24
     rins
    0.24
     vir
    0.23
    isma
    0.23
    ¼
    0.23
    inis
    0.23
    Activations Density 0.021%

    No Known Activations