© 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. 140878
    Prev
    Next
    INDEX
    Explanations

    Extracting numerical data

    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
    Not in Any Lists

    No Comments

    Negative Logits
    bern
    -0.29
    æ´»æĢ§
    -0.26
    械
    -0.26
    keiten
    -0.26
    throw
    -0.25
    rica
    -0.25
    achable
    -0.24
    acious
    -0.24
    ä¸Ŀ毫ä¸į
    -0.24
    ç§ģæľį
    -0.24
    POSITIVE LOGITS
     whereas
    0.25
    èĢĮçİ°åľ¨
    0.25
    æ¯Ķè¾ĥé«ĺ
    0.25
     possibility
    0.24
     representation
    0.24
    主宰
    0.24
     cr
    0.24
    çİ°è´§
    0.23
    tings
    0.23
    _representation
    0.23
    Activations Density 5.768%

    No Known Activations