© 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. 88213
    Prev
    Next
    INDEX
    Explanations

    communication/expression

    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
    Negative Logits
    arena
    -0.28
    idea
    -0.27
    ç¥ĸåħĪ
    -0.26
    åľŁ
    -0.26
     idea
    -0.26
     comps
    -0.24
    èĴľ
    -0.24
    åĮĻ
    -0.24
     Skinny
    -0.23
    ç¾ļ
    -0.23
    POSITIVE LOGITS
    æĶ¶çĽĬçİĩ
    0.26
    ÑijÑĤ
    0.25
    éĺ¶
    0.25
     Ron
    0.25
    åĩĨæŶ
    0.24
    çĽ¸å¯¹äºİ
    0.23
    cade
    0.23
    人æ°ijå¸ģ
    0.23
    @RunWith
    0.23
     mon
    0.23
    Activations Density 17.634%

    No Known Activations