© 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. 64061
    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
    åħ¬çĶ¨
    -0.28
    ä¹ĺ车
    -0.28
    ovich
    -0.26
    onen
    -0.25
    äºĭåĦ¿
    -0.25
    æĭĪ
    -0.24
    为ä»Ģä¹Īè¦ģ
    -0.24
     unsub
    -0.24
    ooting
    -0.24
    onis
    -0.24
    POSITIVE LOGITS
    eur
    0.31
     anyway
    0.26
    egrity
    0.26
    ug
    0.25
    gy
    0.25
     otherwise
    0.25
     accordingly
    0.25
    vg
    0.25
    ek
    0.25
     convention
    0.24
    Activations Density 19.176%

    No Known Activations

    This feature has no known activations.