© 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. 108074
    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
    çļĦéĥ¨åĪĨ
    -0.27
    lightly
    -0.26
    éĹ¨æ§Ľ
    -0.25
    主ä¹īæĢĿæĥ³
    -0.25
     onDataChange
    -0.25
    éĥ¨ä»½
    -0.25
    èĪĮå°ĸ
    -0.25
    å§Ķ
    -0.24
    æ¯ı次éĥ½
    -0.24
    è½
    -0.24
    POSITIVE LOGITS
    kept
    0.27
    åijĬè¯ī她
    0.25
    åħ»
    0.25
     MAS
    0.25
     INC
    0.25
     tie
    0.25
    arda
    0.25
    bst
    0.24
     integration
    0.24
    RIC
    0.24
    Activations Density 2.879%

    No Known Activations

    This feature has no known activations.