© 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. 27-TRANSCODER-HP
    7. 9911
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     completely
    -0.35
     entirely
    -0.32
    å®Įåħ¨
    -0.32
    COMPLETE
    -0.31
    pletely
    -0.29
    å®Įåħ¨æ²¡æľī
    -0.28
     blackout
    -0.28
     theoretical
    -0.26
     completamente
    -0.26
     wholly
    -0.26
    POSITIVE LOGITS
    æłĩ
    0.28
    vais
    0.27
     bil
    0.26
    omics
    0.26
    çĬ¹
    0.25
    hair
    0.25
    ihan
    0.25
    ç»ı
    0.24
    åĮ¾
    0.24
    ;l
    0.24
    Activations Density 0.001%

    No Known Activations