© 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. 107621
    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
    Powered
    -0.29
    çĦĹ
    -0.26
    âľĺ
    -0.26
    .stub
    -0.25
     Victorian
    -0.25
     powered
    -0.25
     Hun
    -0.25
    次è¦ģ
    -0.24
    )!
    -0.23
    )!↵
    -0.23
    POSITIVE LOGITS
     refer
    0.29
    Refer
    0.28
    大大
    0.28
    neas
    0.27
    chy
    0.27
    Dou
    0.27
    Canadian
    0.26
    大åĪĩ
    0.26
    æ¡©
    0.25
    uro
    0.25
    Activations Density 11.780%

    No Known Activations

    This feature has no known activations.