© 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. 129328
    Prev
    Next
    INDEX
    Explanations

    Parentheses with capital letters

    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
     ro
    -0.30
     Cro
    -0.27
     gest
    -0.26
     prep
    -0.26
     cuff
    -0.25
     fer
    -0.25
     rou
    -0.24
    ],č↵
    -0.24
    ;</
    -0.24
     cro
    -0.24
    POSITIVE LOGITS
     ourselves
    0.28
    Describe
    0.27
    .describe
    0.27
     yourselves
    0.26
    .Lang
    0.26
    å¼ij
    0.24
    oto
    0.24
    myfile
    0.23
    tolua
    0.23
    arily
    0.23
    Activations Density 21.180%

    No Known Activations