© 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. 23-TRANSCODER-HP
    7. 23487
    Prev
    Next
    INDEX
    Explanations

    java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    agos
    -0.26
    üb
    -0.26
    交
    -0.25
    nod
    -0.25
    Ä°M
    -0.24
    %M
    -0.24
    olon
    -0.24
    å®ĥ们
    -0.23
    模仿
    -0.23
    æ³¢
    -0.23
    POSITIVE LOGITS
    å¼Ĭ
    0.29
    Refresh
    0.28
     freshly
    0.28
    refresh
    0.27
    èªĬ
    0.26
     fresh
    0.26
    alth
    0.26
    à¸ķà¸Ļ
    0.25
    oti
    0.25
    Fresh
    0.25
    Activations Density 0.004%

    No Known Activations