© 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. 39423
    Prev
    Next
    INDEX
    Explanations

    possessive

    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
    jo
    -0.26
    Jo
    -0.25
     lou
    -0.25
    àªĨ
    -0.25
    åIJ¬çĿĢ
    -0.25
    åĵ¥ä»¬
    -0.25
    濯
    -0.24
    ä¾
    -0.24
    æĦıåij³çĿĢ
    -0.24
     Bundle
    -0.24
    POSITIVE LOGITS
    ç®Ķ
    0.27
    åľ¨æĪijçļĦ
    0.25
    çį»
    0.24
    zon
    0.24
    çĮ®
    0.24
    burgh
    0.24
    åij¨è½¬
    0.24
    _trees
    0.23
     Enumeration
    0.23
    åľ¨ä»ĸ
    0.23
    Activations Density 0.264%

    No Known Activations