© 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. 24178
    Prev
    Next
    INDEX
    Explanations

    Code, documentation, and names

    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
     Garrett
    -0.27
    jÄħ
    -0.27
    ilm
    -0.26
    OUGH
    -0.25
    eday
    -0.25
    ç³»ç»ŁçļĦ
    -0.24
    ä¸įåı¯
    -0.24
    å¿ħä¸įåı¯
    -0.24
    swagger
    -0.24
    ROY
    -0.23
    POSITIVE LOGITS
    æĪİ
    0.32
    esus
    0.27
     Maths
    0.25
    amoto
    0.25
     degrees
    0.25
    åĩĮ
    0.24
    å±ı
    0.23
    oha
    0.23
    })();↵↵
    0.23
     '');↵↵
    0.23
    Activations Density 0.000%

    No Known Activations