© 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. 141963
    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
    untime
    -0.28
    èĮħ
    -0.28
    没æľīä»Ģä¹Ī
    -0.27
    çĵ¢
    -0.26
    èĭŀ
    -0.26
    åıĬåħ¶ä»ĸ
    -0.24
    çķ´
    -0.24
    以åıĬåħ¶ä»ĸ
    -0.24
     anytime
    -0.24
     Serif
    -0.23
    POSITIVE LOGITS
    OND
    0.29
    æī¼
    0.27
    uba
    0.27
    æ³¢åĬ¨
    0.26
    为åĩĨ
    0.26
    äºĨåIJ§
    0.25
    ä¼łæĿ¥
    0.24
    åıijçĶŁ
    0.24
    æĶ
    0.24
    OnError
    0.24
    Activations Density 38.626%

    No Known Activations

    This feature has no known activations.