© 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. 141402
    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
    æ¼Ķ
    -0.29
    áºĵ
    -0.26
    强èĢħ
    -0.25
    æĢ¥éľĢ
    -0.25
    çģ¶
    -0.25
    .arguments
    -0.25
    æĪijèĥ½
    -0.25
    æľ¬æĸĩ
    -0.25
     Zap
    -0.24
    ervative
    -0.24
    POSITIVE LOGITS
    alus
    0.36
    å¤ļä½Ļ
    0.28
    æģ¶æĢ§
    0.26
    REFER
    0.26
    代åĬŀ
    0.25
    æºŁ
    0.25
     SLOT
    0.25
    eu
    0.25
    æ±Ģ
    0.24
     unique
    0.24
    Activations Density 22.477%

    No Known Activations

    This feature has no known activations.