© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6098
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
    usk
    -0.31
    türk
    -0.28
    fillable
    -0.27
     lên
    -0.27
    ãģ¨ãģ«
    -0.26
    inka
    -0.25
     Kurd
    -0.24
    çįĴ
    -0.24
    ulton
    -0.23
    åĮºåĨħ
    -0.23
    POSITIVE LOGITS
    if
    0.28
    elt
    0.28
       ↵
    0.28
    纵
    0.28
     synd
    0.28
      ↵
    0.28
     typically
    0.26
     extra
    0.26
     TV
    0.26
    æģķ
    0.26
    Activations Density 0.044%

    No Known Activations