© 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. 8678
    Prev
    Next
    INDEX
    Explanations

    seas

    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
    ukes
    -0.32
    uper
    -0.29
    åģļä¸ĢäºĽ
    -0.27
    uke
    -0.27
    bout
    -0.27
    udios
    -0.26
     Tested
    -0.25
    stras
    -0.25
    uron
    -0.25
    keit
    -0.25
    POSITIVE LOGITS
    å¼·ãģĦ
    0.27
     blossom
    0.27
    å¼¹
    0.24
     yük
    0.24
    æĸŃ
    0.24
    çĴĢçĴ¨
    0.24
     Bloss
    0.24
    ãģ§ãģįãģŁ
    0.23
     Interstate
    0.23
    طار
    0.23
    Activations Density 0.281%

    No Known Activations