© 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. 130543
    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
    sta
    -0.28
    ][/
    -0.27
    stable
    -0.26
    âĮ¡
    -0.26
    ä¹Ĵ
    -0.25
    éĢļçŁ¥ä¹¦
    -0.25
    形容
    -0.24
     commem
    -0.24
    éĥ½è¯´
    -0.24
    zl
    -0.24
    POSITIVE LOGITS
    inke
    0.25
    ayer
    0.24
    åĥ§
    0.24
    æľºçĶµ
    0.23
    uve
    0.23
    æĪIJé¾Ļ
    0.23
     LOCAL
    0.23
    	IL
    0.23
     mano
    0.22
    ICS
    0.22
    Activations Density 34.330%

    No Known Activations

    This feature has no known activations.