© 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. 20-TRANSCODER-HP
    7. 142548
    Prev
    Next
    INDEX
    Explanations

    programming queries

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    åĴķ
    -0.29
    éĩijå±±
    -0.27
     Germ
    -0.26
    __.__
    -0.26
     Cry
    -0.26
    psc
    -0.26
    urved
    -0.25
    activex
    -0.25
    atics
    -0.25
     Nurse
    -0.24
    POSITIVE LOGITS
    è¿Ľ
    0.29
    (confirm
    0.28
    鬼
    0.27
    ç»ıè¿ĩ
    0.27
    代表
    0.26
    æľĢç»Ī
    0.26
    ayah
    0.26
    deg
    0.25
    å®ļä¹ī
    0.25
     defin
    0.25
    Activations Density 0.303%

    No Known Activations