© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63568
    Prev
    Next
    INDEX
    Explanations

    US patents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    社ä¼ļèµĦæľ¬
    -0.32
    åıįè¿ĩæĿ¥
    -0.28
    伯
    -0.26
    俾
    -0.26
    LEY
    -0.26
     bl
    -0.25
    leys
    -0.25
    大人
    -0.24
    .selenium
    -0.24
    _figure
    -0.24
    POSITIVE LOGITS
    æĸ°åĮº
    0.28
    iming
    0.27
     Diff
    0.27
    cola
    0.26
    å§ĵ
    0.26
    -main
    0.25
    æ¿Ł
    0.24
    æĢ§å¼º
    0.24
    colo
    0.24
    Jimmy
    0.24
    Activations Density 70.565%

    No Known Activations