© 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. 19453
    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
     Naked
    -0.32
    aker
    -0.26
    Tpl
    -0.26
    ICA
    -0.26
    足
    -0.25
    à¸ļà¸Ĺ
    -0.25
    è´¢
    -0.25
    alles
    -0.25
    çŀ³
    -0.25
     (_)
    -0.24
    POSITIVE LOGITS
    被害
    0.30
     shots
    0.28
    åį«çĶŁ
    0.26
    partial
    0.26
    rz
    0.26
     boundaries
    0.25
    ews
    0.25
    epy
    0.24
    ewed
    0.24
    endants
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.