© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107526
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ulia
    -0.27
    é¦
    -0.26
     Gratuit
    -0.24
    ographics
    -0.24
    åīįåĪĹ
    -0.23
    quo
    -0.23
    ologna
    -0.23
    olve
    -0.23
     silk
    -0.22
    ä½Ļ
    -0.22
    POSITIVE LOGITS
    rophy
    0.26
    ubes
    0.25
    rosse
    0.24
    ç¬ŀ
    0.23
     convictions
    0.23
    .prot
    0.23
    管çIJĨä¸Ńå¿ĥ
    0.23
    ÑĢÑı
    0.23
    æĢİ
    0.22
    çĶij
    0.22
    Activations Density 23.259%

    No Known Activations

    This feature has no known activations.