© 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. 22-TRANSCODER-HP
    7. 112831
    Prev
    Next
    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     revealed
    -0.32
     inferred
    -0.31
    ä¼łæĿ¥
    -0.29
    éĢıéľ²
    -0.29
    -ind
    -0.28
     hear
    -0.28
    æĬ¥éģĵ
    -0.28
    éĢı
    -0.28
     reveals
    -0.28
    ind
    -0.28
    POSITIVE LOGITS
    Wik
    0.28
     popular
    0.27
    odon
    0.26
     Wikipedia
    0.25
    飽
    0.25
     اÙĦÙĨÙĤد
    0.25
    çļĦåĸľçĪ±
    0.25
     withdrawn
    0.25
    Wiki
    0.24
    popular
    0.24
    Activations Density 0.000%

    No Known Activations