© 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. 22034
    Prev
    Next
    INDEX
    Explanations

    single-digit numbers

    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
    åĬłéĩį
    -0.27
    Cancelable
    -0.26
    NSObject
    -0.25
    /span
    -0.24
     Popular
    -0.24
    plural
    -0.23
    Builders
    -0.23
    éĢŀ
    -0.23
    /cloud
    -0.23
     rec
    -0.23
    POSITIVE LOGITS
     fits
    0.26
    oleon
    0.25
    amide
    0.25
    anine
    0.25
    agon
    0.24
    騰
    0.24
    ler
    0.24
    ä¸įåIJĮ
    0.24
    enstein
    0.24
    fte
    0.24
    Activations Density 0.313%

    No Known Activations