© 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. 107515
    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
    Alias
    -0.27
    çľĭäºĨ
    -0.26
     foe
    -0.25
    èģĶ缣
    -0.25
    inion
    -0.25
    inue
    -0.25
     Ally
    -0.24
    çĸ
    -0.24
    MLS
    -0.24
    ä¿ļ
    -0.24
    POSITIVE LOGITS
     aspir
    0.29
    åľ¨çݩ家
    0.28
    aksi
    0.27
    åij³
    0.27
    DOMContentLoaded
    0.26
     everything
    0.25
    antu
    0.25
    éĤ£ä¸Ģ
    0.25
    acies
    0.24
    ä¸ĢåĪĩ
    0.24
    Activations Density 0.045%

    No Known Activations

    This feature has no known activations.