© 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. 108732
    Prev
    Next
    INDEX
    Explanations

    Methods and Strategies

    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
    DataContext
    -0.27
    edi
    -0.27
    ips
    -0.25
    å¾Īéĩįè¦ģçļĦ
    -0.25
    èħ»
    -0.25
    anan
    -0.25
    _greater
    -0.25
    娴
    -0.24
    æľĢåħ³éĶ®çļĦ
    -0.24
    âĺģ
    -0.24
    POSITIVE LOGITS
    éĢīè´Ń
    0.27
    turned
    0.27
    ãģ°ãģĭãĤĬ
    0.26
    аниÑĨ
    0.25
     turnovers
    0.24
     ck
    0.24
    ów
    0.24
    åľ¨åĽ½å¤ĸ
    0.24
    cmath
    0.24
    人士
    0.24
    Activations Density 26.445%

    No Known Activations