© 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. 12-TRANSCODER-HP
    7. 22039
    Prev
    Next
    INDEX
    Explanations

    race and discrimination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç²Ĺ
    -0.30
    Hier
    -0.28
     Hier
    -0.27
    ä¹Ŀå·ŀ
    -0.27
    ISC
    -0.27
    stances
    -0.26
    _CODES
    -0.26
    æ¦ľåįķ
    -0.25
    åıĸ
    -0.24
     hierarchical
    -0.24
    POSITIVE LOGITS
    wish
    0.29
    [arr
    0.26
    èĬ
    0.26
    èĤĩäºĭ
    0.25
    æĴħ
    0.24
     possession
    0.24
     humble
    0.24
     caul
    0.24
    å¨ĺ家
    0.24
    çļĦæł·åŃIJ
    0.23
    Activations Density 0.000%

    No Known Activations