© 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. 107984
    Prev
    Next
    INDEX
    Explanations

    ary

    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
     rou
    -0.31
     PLA
    -0.27
     dances
    -0.26
    浪漫
    -0.26
     dance
    -0.26
    zer
    -0.26
    &page
    -0.26
    åįķä½į
    -0.25
    æľīä¸ĢäºĽ
    -0.24
    计åĪĴçĶŁèĤ²
    -0.24
    POSITIVE LOGITS
    ---č↵
    0.26
    }}}
    0.26
    INLINE
    0.25
    âĤĬ
    0.25
    obutton
    0.24
    mainwindow
    0.24
    çªĹå¤ĸ
    0.24
    é¢ļ
    0.24
     Hoff
    0.23
     conform
    0.23
    Activations Density 6.284%

    No Known Activations