© 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. 64606
    Prev
    Next
    INDEX
    Explanations

    Ordinal numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     previous
    -0.28
    paralleled
    -0.28
     Previous
    -0.27
     preced
    -0.26
    astle
    -0.25
    previous
    -0.25
    çĥĪ
    -0.25
     précéd
    -0.25
    preced
    -0.25
    ä»ĸ说
    -0.24
    POSITIVE LOGITS
    pty
    0.31
    amental
    0.30
    ’ex
    0.28
     Aval
    0.27
    æ¶Ķ
    0.26
     itch
    0.26
    oping
    0.25
    Such
    0.25
    ORY
    0.25
    plx
    0.25
    Activations Density 4.820%

    No Known Activations