© 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. 9806
    Prev
    Next
    INDEX
    Explanations

    Business and data analysis

    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
    antro
    -0.27
     furthermore
    -0.26
    称ä¹ĭ为
    -0.26
     zusätzlich
    -0.26
    è¦ģä¹Ī
    -0.26
     jednoc
    -0.25
    imitives
    -0.24
    obi
    -0.24
    åIJĮå¹´
    -0.24
     afterwards
    -0.24
    POSITIVE LOGITS
     Problem
    0.33
     vs
    0.31
    æĺ¯ä¸Ģ个
    0.31
     Program
    0.29
     Project
    0.29
     Simulation
    0.29
     Exercise
    0.29
     Dataset
    0.29
    ↵                ↵
    0.29
     Issue
    0.28
    Activations Density 0.465%

    No Known Activations