© 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. 54077
    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
    æĮĩ
    -0.28
     staple
    -0.26
     staples
    -0.25
    è¿ŀ
    -0.25
    çļĦç«ŀäºī
    -0.24
    æIJ¶
    -0.24
     jugg
    -0.23
    æľĢ主è¦ģ
    -0.23
    (ptr
    -0.23
    avana
    -0.23
    POSITIVE LOGITS
    acre
    0.32
    ·æĸ°
    0.25
    simulate
    0.24
     cÆ°á»Ŀi
    0.24
    accent
    0.24
    isson
    0.24
    裨
    0.24
     двигаÑĤел
    0.24
    isions
    0.24
     McCart
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.