© 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. 23616
    Prev
    Next
    INDEX
    Explanations

    to

    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
    å¦Ī
    -0.27
    eros
    -0.25
    çļĦä¸ĢåĪĩ
    -0.24
    pollo
    -0.24
    åijĬçŁ¥
    -0.24
     would
    -0.24
    æĪij们ä¼ļ
    -0.23
    åIJĦ个çݯèĬĤ
    -0.23
    ä¸ĭ
    -0.23
    kits
    -0.23
    POSITIVE LOGITS
    åıijæĮ¥
    0.29
    olley
    0.27
    ยะ
    0.26
    agy
    0.26
    iless
    0.25
    oth
    0.25
    obao
    0.25
    â¬ħ
    0.24
    uib
    0.24
    åIJįä¹ī
    0.24
    Activations Density 0.008%

    No Known Activations