© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4827
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¹²é¢Ħ
    -0.28
    aks
    -0.26
    OnInit
    -0.26
    ands
    -0.26
    OPS
    -0.26
     ^↵
    -0.26
    æĭŁå®ļ
    -0.25
    -spin
    -0.24
     cri
    -0.24
    åı¯ä»¥æĽ´å¥½
    -0.24
    POSITIVE LOGITS
     Zap
    0.26
    azer
    0.24
    idel
    0.24
     réserve
    0.24
    Know
    0.24
    ÑıÑĤÑĮ
    0.24
    lav
    0.23
    execution
    0.23
    /logging
    0.23
    blank
    0.23
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.