© 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. 18855
    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
    vern
    -0.26
    (mp
    -0.25
     auto
    -0.25
    orpor
    -0.25
    à¸į
    -0.25
     amp
    -0.25
    fest
    -0.24
    uter
    -0.24
     ser
    -0.24
     offic
    -0.24
    POSITIVE LOGITS
     east
    0.29
    è´¨
    0.27
    åIJij举
    0.26
    бл
    0.26
    lige
    0.25
    举
    0.24
    寡
    0.24
    istle
    0.24
    質
    0.24
     East
    0.24
    Activations Density 23.939%

    No Known Activations

    This feature has no known activations.