© 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. 142412
    Prev
    Next
    INDEX
    Explanations

    settings

    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
    æŃ¥æŃ¥
    -0.26
    èĩªè´¸åĮº
    -0.25
    åĴĮå°ļ
    -0.25
    ldre
    -0.25
    aware
    -0.24
    åĿĩæľī
    -0.24
    åĿĩåı¯
    -0.24
    顶å±Ĥ
    -0.24
    %^
    -0.24
    icol
    -0.23
    POSITIVE LOGITS
    /process
    0.29
     peu
    0.28
    å¥ļ
    0.27
    è§ģè¯ģ
    0.25
    级以ä¸Ĭ
    0.24
     menj
    0.23
     Limit
    0.23
     deserving
    0.23
    ä¹ĭ声
    0.23
     emerged
    0.23
    Activations Density 10.882%

    No Known Activations