© 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. 142346
    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
    滩
    -0.29
    IRT
    -0.29
     tele
    -0.29
    åŃ½
    -0.27
    ä¸ļ
    -0.26
    迹象
    -0.26
    åıĮæĸ¹
    -0.26
    两边
    -0.26
    梦æĥ³
    -0.25
    HP
    -0.25
    POSITIVE LOGITS
    è¯ļå®ŀ
    0.28
     Teil
    0.27
    ä¸Ĭæ¼Ķ
    0.27
    åī¯ç§ĺ书éķ¿
    0.26
    mus
    0.25
    Mus
    0.25
    ury
    0.25
    orton
    0.24
    éģıåĪ¶
    0.24
    âĹ»
    0.24
    Activations Density 46.431%

    No Known Activations

    This feature has no known activations.