© 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. 63796
    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
    èĩ´çĶµ
    -0.29
     negot
    -0.27
    çļĦä¿¡æģ¯
    -0.27
    lobber
    -0.25
     informação
    -0.25
    -ra
    -0.24
     Press
    -0.24
    对ä»ĸ
    -0.24
    áĥĸ
    -0.24
    æĬ¤
    -0.24
    POSITIVE LOGITS
     universal
    0.27
    variant
    0.27
    Variant
    0.26
    éĢŀ
    0.26
    variants
    0.26
    å¸Ń
    0.26
    ä¸ĩ
    0.26
    achi
    0.26
    ben
    0.25
    Universal
    0.25
    Activations Density 13.532%

    No Known Activations

    This feature has no known activations.