© 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. 130519
    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
    THR
    -0.33
     THR
    -0.29
     ********************************************************
    -0.28
    æ¯Ĺ
    -0.27
    /@
    -0.27
    atsby
    -0.26
    åĴĮ个人
    -0.26
    hare
    -0.25
    åİ»åĵªåĦ¿
    -0.25
     ****************************************************************
    -0.25
    POSITIVE LOGITS
    éĵĦ
    0.32
     reput
    0.28
    åºĹéĩĮ
    0.28
    åħ°
    0.27
    ileged
    0.27
    éĩį伤
    0.27
    ized
    0.27
    artz
    0.25
     Nurs
    0.25
    çī¹åĪ«
    0.25
    Activations Density 2.792%

    No Known Activations

    This feature has no known activations.