© 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. 129589
    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
    ÑĨион
    -0.28
     å®
    -0.26
     counterpart
    -0.26
    æł¡
    -0.25
    AVOR
    -0.25
    éĢĢ
    -0.24
    CSR
    -0.24
     ret
    -0.23
    ç´§
    -0.23
    _mentions
    -0.23
    POSITIVE LOGITS
    çݯ
    0.28
    scribed
    0.27
    (public
    0.26
     Tops
    0.25
    ermann
    0.25
    ubs
    0.24
    æĸ°å¨ĺ
    0.24
    æĬķèµĦé¢Ŀ
    0.24
    igned
    0.24
    åѦ龸
    0.24
    Activations Density 3.655%

    No Known Activations

    This feature has no known activations.