© 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. 33-TRANSCODER-HP
    7. 53316
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĢÑĥд
    -0.28
     Sand
    -0.28
     Âł Âł
    -0.27
    åı®
    -0.27
    ÑĥÑĢ
    -0.26
     á»ķn
    -0.26
    stell
    -0.25
    ج
    -0.25
    ATA
    -0.25
    Sand
    -0.24
    POSITIVE LOGITS
    ponsored
    0.27
    æĮĩçļĦæĺ¯
    0.27
     favoured
    0.26
    ugins
    0.26
    羡æħķ
    0.26
    ubs
    0.25
    ourmet
    0.24
    çĸĥ
    0.24
    preferred
    0.24
    PerPixel
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.