© 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. 4740
    Prev
    Next
    INDEX
    Explanations

    Pyramids and related words

    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
    æĹłå£°
    -0.29
    .va
    -0.27
    é©»
    -0.27
    åī©
    -0.27
    æĸ¹å¼ıè¿Ľè¡Į
    -0.26
     Compatibility
    -0.26
    _NC
    -0.25
    å¾Ģäºĭ
    -0.25
    lec
    -0.24
    ÑĪе
    -0.24
    POSITIVE LOGITS
    URATION
    0.24
     intuit
    0.24
    èĻİ
    0.23
    éĿĪ
    0.23
     tÃŃ
    0.23
    åĨ³èµĽ
    0.23
     deltas
    0.23
    globals
    0.23
    itals
    0.22
    太
    0.22
    Activations Density 0.013%

    No Known Activations