© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7114
    Prev
    Next
    INDEX
    Explanations

    Articles and pronouns

    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
    olest
    -0.28
    è¥ģ
    -0.27
    个交æĺĵ
    -0.25
    orio
    -0.25
     Biggest
    -0.25
    ulta
    -0.24
    Dead
    -0.24
     żyw
    -0.24
     Frem
    -0.24
    erno
    -0.24
    POSITIVE LOGITS
    ç§ijæĬĢèĤ¡ä»½
    0.26
    åıįæŃ£
    0.26
    çĤ¹è¯Ħ
    0.26
    è¿Ļåıª
    0.26
    LBL
    0.26
     bask
    0.24
    主æĦı
    0.24
    amer
    0.24
    çľ¼éķľ
    0.24
    èĩ´
    0.24
    Activations Density 0.150%

    No Known Activations