© 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. 90351
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    ucus
    -0.28
    ä¹Łä¸įæĺ¯
    -0.27
    ogh
    -0.26
    ymb
    -0.26
     moment
    -0.25
    âĩĵ
    -0.25
    leck
    -0.25
    åħ³éĶ®æŶåĪ»
    -0.24
    itals
    -0.24
    åħ¨äº§ä¸ļéĵ¾
    -0.24
    POSITIVE LOGITS
    agra
    0.28
    帮
    0.26
    åIJĪ
    0.26
    è¿ŀ
    0.25
    stances
    0.25
    两åı¥
    0.25
     TERMS
    0.25
    å·¥ç¨ĭè´¨éĩı
    0.24
    ä»ĸçŁ¥éģĵ
    0.24
    åİĨ
    0.24
    Activations Density 2.947%

    No Known Activations