© 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. 27-TRANSCODER-HP
    7. 58541
    Prev
    Next
    INDEX
    Explanations

    Cultural identity/ethnicity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åºĬä¸Ĭ
    -0.26
    itar
    -0.26
    usk
    -0.25
     tasting
    -0.24
     unidentified
    -0.24
     ips
    -0.23
    selectAll
    -0.23
     asym
    -0.23
     gu
    -0.23
     vit
    -0.23
    POSITIVE LOGITS
     UClass
    0.33
    èĢģ人家
    0.27
    ões
    0.26
    roe
    0.26
    rox
    0.25
    çĶŁåij½çļĦ
    0.25
    Ñĥй
    0.25
    _ERRORS
    0.24
     sammen
    0.24
    SEN
    0.24
    Activations Density 0.001%

    No Known Activations