© 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. 31-TRANSCODER-HP
    7. 19099
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @pytest
    -0.29
    Axes
    -0.27
    ursors
    -0.27
    @g
    -0.26
    好人
    -0.26
    稿
    -0.26
     PURE
    -0.25
    @↵↵
    -0.25
    PURE
    -0.25
     Valley
    -0.25
    POSITIVE LOGITS
    sync
    0.27
    ello
    0.26
    社ä¼ļåıijå±ķ
    0.25
    enne
    0.24
    æīįçŁ¥éģĵ
    0.24
    ron
    0.24
    ä¸Ńå°ıåŀĭ
    0.24
    æľĢå¿«çļĦ
    0.24
     therap
    0.24
    èIJ¥åķĨ
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.