© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129236
    Prev
    Next
    INDEX
    Explanations

    Technical discussions and problem-solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    代
    -0.28
    åıįèĢĮ
    -0.27
    ä»£æĽ¿
    -0.26
    åıįåĢĴ
    -0.25
    hea
    -0.25
    VML
    -0.25
     DISP
    -0.24
    çļĦ帮åĬ©ä¸ĭ
    -0.24
    upon
    -0.24
    åĶ¯
    -0.24
    POSITIVE LOGITS
    èĻİ
    0.26
    izin
    0.25
     ladder
    0.24
    lich
    0.24
    ações
    0.24
    *ft
    0.24
    ãģ¹ãģį
    0.24
    lop
    0.24
     quarter
    0.24
     "|"
    0.24
    Activations Density 21.864%

    No Known Activations