© 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. 24143
    Prev
    Next
    INDEX
    Explanations

    Australia

    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
     Diss
    -0.28
    standing
    -0.28
    æ§Ľ
    -0.27
     diss
    -0.26
     holding
    -0.26
     Brit
    -0.26
    ç»´æĬ¤
    -0.26
    ablish
    -0.26
     Holding
    -0.25
    åĽ¢ä½ĵ
    -0.25
    POSITIVE LOGITS
    awn
    0.28
    hk
    0.27
    elines
    0.27
    使åij½
    0.27
    á»ĭa
    0.26
    秩
    0.26
    hud
    0.25
    iya
    0.25
    åĿĩ线
    0.24
    á»ĭch
    0.24
    Activations Density 0.002%

    No Known Activations