© 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. 90077
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    eah
    -0.28
    yah
    -0.28
    æĹ©çĤ¹
    -0.27
     Ging
    -0.25
    ScreenState
    -0.24
    åį¯
    -0.24
    éĻįèĩ³
    -0.24
    便ä¼ļ
    -0.24
    ä¾¦å¯Ł
    -0.24
    indexes
    -0.23
    POSITIVE LOGITS
     Achilles
    0.24
    unicorn
    0.24
    -clock
    0.24
    çı
    0.24
    enti
    0.24
    ĴĮ
    0.23
    onte
    0.23
     traf
    0.23
     vending
    0.23
    ä¸Ĭä¸ĭ
    0.23
    Activations Density 1.618%

    No Known Activations

    This feature has no known activations.