© 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. 5169
    Prev
    Next
    INDEX
    Explanations

    Code or markup language

    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
    ImageContext
    -0.28
    ivet
    -0.27
    IALOG
    -0.25
    ApiClient
    -0.25
    è¶Ĭæĺ¯
    -0.25
     resil
    -0.25
    á»ijt
    -0.24
    merc
    -0.24
    /org
    -0.24
    ç»·
    -0.23
    POSITIVE LOGITS
    ISS
    0.28
    ç¨Ģ
    0.26
    MAC
    0.25
    麻
    0.25
     combined
    0.25
    itor
    0.25
     dil
    0.25
     implies
    0.25
    رس
    0.25
     continuous
    0.24
    Activations Density 0.001%

    No Known Activations