© 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. 140651
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    ocale
    -0.28
    游
    -0.27
    ctica
    -0.27
    essay
    -0.26
    ark
    -0.26
    ewise
    -0.25
    å°Ŀ
    -0.25
    -focused
    -0.24
    ipation
    -0.24
     Radar
    -0.24
    POSITIVE LOGITS
     HOLDERS
    0.36
    å¸Ń
    0.26
    acers
    0.26
    éªĵ
    0.26
    zá
    0.25
    still
    0.25
    éĻ¬
    0.25
    åĬ¿å¿ħ
    0.25
    æ²Ł
    0.25
    niest
    0.24
    Activations Density 1.549%

    No Known Activations