© 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. 19174
    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
    ä¹Łæĺ¯å¦ĤæѤ
    -0.28
    å¢ŀéĢŁ
    -0.25
    OOM
    -0.25
    asser
    -0.25
    pread
    -0.25
    "..
    -0.25
    çĶŁæ´»ä¹łæĥ¯
    -0.24
    ä¸Ńåħ±
    -0.24
    ium
    -0.24
    kj
    -0.24
    POSITIVE LOGITS
    翼
    0.28
    临
    0.26
     sym
    0.25
    ä½į
    0.25
    atif
    0.24
     means
    0.24
    à¸ĩ
    0.23
     wing
    0.23
    tid
    0.23
    èħķ
    0.23
    Activations Density 2.963%

    No Known Activations

    This feature has no known activations.