© 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. 6698
    Prev
    Next
    INDEX
    Explanations

    Code examples

    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
    eware
    -0.27
    èĪŀ
    -0.26
    otte
    -0.25
     chops
    -0.25
     getCount
    -0.25
    æľīè¶³å¤ŁçļĦ
    -0.24
    iqu
    -0.24
    grades
    -0.24
    -publish
    -0.24
     camper
    -0.24
    POSITIVE LOGITS
     peel
    0.27
    è¬Ŀ
    0.25
     downs
    0.25
    é¢Ĩåıĸ
    0.25
    æĺ¯ä¸ºäºĨ
    0.24
     stained
    0.24
    MIC
    0.24
    replacement
    0.24
    lah
    0.24
    pek
    0.24
    Activations Density 0.006%

    No Known Activations