© 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. 130217
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èļĮ
    -0.29
     اÙĦØŃاÙĦ
    -0.26
    æ²Ľ
    -0.26
     Medium
    -0.25
    åħ¨åĽ½äººæ°ij
    -0.25
     inh
    -0.24
    _drv
    -0.23
    ä»ĭè´¨
    -0.23
     screen
    -0.23
    é¹ħ
    -0.23
    POSITIVE LOGITS
    æĮĩ示
    0.27
    æľīå¤ļå°ij
    0.27
    éĢIJ
    0.27
    adoras
    0.26
    mana
    0.26
    解
    0.26
    agra
    0.26
    票
    0.25
     Junction
    0.25
    éĥ½ä¸įæķ¢
    0.25
    Activations Density 21.163%

    No Known Activations

    This feature has no known activations.