© 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. 7390
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    大纲
    -0.27
    æĪIJåĬŁ
    -0.25
    inus
    -0.24
    æĢ¥äºİ
    -0.24
    *:
    -0.24
    ycl
    -0.23
    (reference
    -0.23
     phản
    -0.23
    inke
    -0.23
    空åīį
    -0.23
    POSITIVE LOGITS
    æ¡ij
    0.27
    Visual
    0.25
    talk
    0.25
     Squ
    0.25
    æĮĤ
    0.24
    Semaphore
    0.24
    纺
    0.23
    家ä¼Ļ
    0.23
    доÑĢ
    0.23
    åĽ¢ç»ĵ
    0.23
    Activations Density 1.074%

    No Known Activations

    This feature has no known activations.