© 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. 107033
    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
    ousy
    -0.29
    ç»ıå¼Ģ
    -0.27
    ivi
    -0.26
    кеÑĢ
    -0.26
    ersed
    -0.26
    inely
    -0.25
    lias
    -0.24
    mis
    -0.24
    Neill
    -0.24
    inode
    -0.24
    POSITIVE LOGITS
    æĸĩ
    0.28
    æĽĻ
    0.26
     GenerationType
    0.25
     VO
    0.24
     repmat
    0.24
    éħ£
    0.24
     nargin
    0.23
     refere
    0.23
    reet
    0.23
     })).
    0.23
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.