© 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. 18-TRANSCODER-HP
    7. 89871
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adamente
    -0.31
    wipe
    -0.27
     XM
    -0.26
     (),↵
    -0.26
    -stop
    -0.26
    XMLElement
    -0.25
    æĹĮ
    -0.25
    ä¼´éļı
    -0.25
    æ´ŀ
    -0.25
    çīĮ
    -0.25
    POSITIVE LOGITS
    ä¹ĥ
    0.29
     Whoever
    0.28
    airo
    0.27
    lord
    0.25
    ä¸Ģæĸ¹
    0.25
     owner
    0.25
    è¿Ļå¼ł
    0.25
    æľ«
    0.25
    acious
    0.24
    ark
    0.24
    Activations Density 1.628%

    No Known Activations

    This feature has no known activations.