© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88476
    Prev
    Next
    INDEX
    Explanations

    Code and math text

    np_max-act · gemini-2.0-flash
    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
    ..<
    -0.31
    č↵↵
    -0.29
    +</
    -0.27
     separate
    -0.27
    çĽ¸å¯¹
    -0.27
    )\↵
    -0.27
    >\↵
    -0.27
     tips
    -0.26
    广
    -0.26
     correct
    -0.26
    POSITIVE LOGITS
    arsity
    0.27
    Enums
    0.25
    æľīæķĪæĢ§
    0.24
    æĿĥå¨ģ
    0.24
     automat
    0.24
    imp
    0.24
    everyone
    0.23
    人èĦ¸è¯ĨåĪ«
    0.23
    ITT
    0.23
    SEL
    0.23
    Activations Density 2.569%

    No Known Activations