© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19931
    Prev
    Next
    INDEX
    Explanations

    Different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĥŁçģ«
    -0.28
    çļ®èĤ¤çĹħ
    -0.28
    åĬŀæ³ķ
    -0.27
    ä»ĸ们ä¼ļ
    -0.25
    ATEGORY
    -0.25
    angkan
    -0.25
    身影
    -0.25
     Ai
    -0.24
    addTo
    -0.24
    VENT
    -0.24
    POSITIVE LOGITS
    å®ŀçİ°äºĨ
    0.32
     corr
    0.28
    ä¸įä»ħ
    0.28
    常
    0.28
     sill
    0.27
    èµ°
    0.27
    åĪĽéĢłäºĨ
    0.27
    æĮģãģ£ãģ¦ãģĦ
    0.27
    Subsystem
    0.27
    è¾¾åĪ°äºĨ
    0.26
    Activations Density 1.192%

    No Known Activations