© 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. 19283
    Prev
    Next
    INDEX
    Explanations

    Programming/Database context

    np_max-act-logits · gemini-2.0-flash
    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
    åľº
    -0.32
     copyrighted
    -0.27
     quant
    -0.27
    缶
    -0.25
     Field
    -0.25
     Tango
    -0.25
    .quant
    -0.25
    TX
    -0.25
    åIJĪæł¼
    -0.25
     field
    -0.25
    POSITIVE LOGITS
    çĸ£
    0.29
    认
    0.28
    getInstance
    0.26
    çĦī
    0.25
    avo
    0.25
    gra
    0.25
    åĶij
    0.24
    å¸ij
    0.24
    åī¯æĢ»è£ģ
    0.24
    arguments
    0.24
    Activations Density 0.109%

    No Known Activations