© 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. 107412
    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
    .lesson
    -0.26
    mare
    -0.24
    ä¸įå®ľ
    -0.24
    èĿ°
    -0.24
    addError
    -0.24
    éĢīåĩº
    -0.24
    _INCREMENT
    -0.23
     Croatia
    -0.23
     повеÑĢ
    -0.23
     Maple
    -0.23
    POSITIVE LOGITS
    æĶ¸
    0.28
    Mui
    0.27
    ous
    0.27
    è¿Ļè¾¹
    0.26
    ä¹ŁçŁ¥éģĵ
    0.26
    èĩªæĪij
    0.26
     heter
    0.25
    åĶ¤
    0.25
    çļĦä¿¡ä»»
    0.25
     Partner
    0.25
    Activations Density 2.127%

    No Known Activations

    This feature has no known activations.