© 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. 9166
    Prev
    Next
    INDEX
    Explanations

    varied text snippets

    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
     favoured
    -0.24
    主导
    -0.24
    DataMember
    -0.24
    ounge
    -0.24
    bay
    -0.24
    è´¯
    -0.23
    åºŃéĻ¢
    -0.23
    è¶³å¤ŁçļĦ
    -0.23
    æĦŁåºĶ
    -0.23
     favored
    -0.23
    POSITIVE LOGITS
    åĽ½äºº
    0.28
     separated
    0.28
    åĪĨ离
    0.28
    				↵				↵
    0.26
     nämlich
    0.25
     separation
    0.25
     Specification
    0.24
     slate
    0.24
    ft
    0.24
    åĥı
    0.24
    Activations Density 0.038%

    No Known Activations