© 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. 108553
    Prev
    Next
    INDEX
    Explanations

    and or

    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
    鼶
    -0.29
    REEN
    -0.27
    ĥģ
    -0.27
    )||(
    -0.26
     sung
    -0.25
     zero
    -0.25
     Zero
    -0.25
     ZERO
    -0.24
    ä¹Łä¸įè¦ģ
    -0.24
    ä¹Łæ²¡
    -0.24
    POSITIVE LOGITS
    inite
    0.27
    brit
    0.26
    svp
    0.25
    常å§Ķ
    0.25
    离
    0.25
     stole
    0.24
    atchet
    0.24
     Goodman
    0.24
    perm
    0.23
    ROUND
    0.23
    Activations Density 22.438%

    No Known Activations