© 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. 108783
    Prev
    Next
    INDEX
    Explanations

    Adam

    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
    æŨ
    -0.28
    ılıyor
    -0.26
    çĽĬ
    -0.26
    veau
    -0.25
    rawid
    -0.25
    ãģ¿ãģª
    -0.24
    orama
    -0.24
    oir
    -0.24
    ailable
    -0.24
    ómo
    -0.24
    POSITIVE LOGITS
    son
    0.26
    æĭĬ
    0.26
    ä¸Ģè§Ĵ
    0.24
    éķ¿çĽ¸
    0.24
    æĭIJ
    0.23
     Icelandic
    0.23
     blender
    0.23
    à¹Ģà¸Ĺà¸ŀ
    0.23
    èĢģ家
    0.23
    Employ
    0.23
    Activations Density 1.184%

    No Known Activations