© 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. 14-TRANSCODER-HP
    7. 41711
    Prev
    Next
    INDEX
    Explanations

    Exclamations/Code Syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     dynam
    -0.25
     Tiger
    -0.25
     expiresIn
    -0.24
    panion
    -0.24
     Cannon
    -0.24
     trigger
    -0.24
    ä¼ģä¸ļæıIJä¾Ľ
    -0.23
     Trigger
    -0.23
     Citation
    -0.23
     mus
    -0.23
    POSITIVE LOGITS
    adem
    0.27
    ç¡®
    0.27
    oland
    0.25
    åij¨
    0.25
    æİĮ
    0.24
    æ¸ħåįİ
    0.24
    Circular
    0.24
     settled
    0.23
    thane
    0.23
    为ä¹ĭ
    0.23
    Activations Density 0.303%

    No Known Activations