© 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. 20-TRANSCODER-HP
    7. 140543
    Prev
    Next
    INDEX
    Explanations

    Qualifying statements/exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    opoulos
    -0.27
    éĢ¼è¿ij
    -0.26
    èıĬ
    -0.25
    ä»Ģä¹Īåij¢
    -0.25
     ters
    -0.25
    åºĬä¸Ĭ
    -0.24
    çģ°èī²
    -0.24
    交åıī
    -0.24
    ãģ¤ãģį
    -0.24
    aben
    -0.24
    POSITIVE LOGITS
    éķ¿è¾Ī
    0.27
    leave
    0.24
     Familie
    0.24
    è´¢çī©
    0.24
    eliac
    0.24
     domina
    0.24
    éĥ¨éŨ
    0.24
     aba
    0.24
    鸳
    0.23
    æ³ķ令
    0.23
    Activations Density 11.736%

    No Known Activations