© 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. 62765
    Prev
    Next
    INDEX
    Explanations

    technical documentation/specifications

    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
    esen
    -0.29
    ardin
    -0.27
    dek
    -0.27
    igmat
    -0.25
    anax
    -0.25
    din
    -0.25
    ulary
    -0.24
    getContext
    -0.24
    inen
    -0.24
    %S
    -0.24
    POSITIVE LOGITS
     permissible
    0.28
    ächt
    0.28
     def
    0.28
     stage
    0.27
    åı²
    0.26
    cons
    0.26
    çĩ®
    0.26
     rec
    0.25
    ä¸Ģèĩ´æĢ§
    0.25
     c
    0.25
    Activations Density 2.028%

    No Known Activations